{
  "benchmark_line": "gamebench2",
  "generated_at": "2026-08-23T20:51:16Z",
  "public_release_id": "gb2-20260823-7d5648862dc8",
  "results_cut_id": "gb2-20260823-7d5648862dc8",
  "schema_version": 2,
  "snapshot_id": "20260823_205116",
  "tracks": {
    "full_freedom/balanced": {
      "GB2-01": [
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 88,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 43,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-fable-5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 26,
          "model": "claude-fable-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-2dbc6efbd7db03b5",
          "rated_matches": 86,
          "raw_elo_rating": 1746.9451046530367,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 71.4108605082153,
          "uncertainty": 9.855626741889738,
          "unilateral_faults": 2,
          "wins": 60
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 0,
          "capped_draws": 0,
          "coverage_status": "pending",
          "distinct_rated_opponents": 0,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "legacy_shared_thinking_budget",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-opus-4-5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "budget",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 0,
          "model": "claude-opus-4-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-7631f602d0516364",
          "rated_matches": 0,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "budget",
          "reasoning_setting": "legacy_shared_thinking_budget",
          "repair_status": "first_pass",
          "unilateral_faults": 0,
          "wins": 0
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 178,
          "capped_draws": 51,
          "coverage_status": "rated",
          "distinct_rated_opponents": 72,
          "draws": 51,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-opus-4-5",
            "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 43,
          "model": "claude-opus-4-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-829b603611fbdcef",
          "rated_matches": 178,
          "raw_elo_rating": 1593.5115898273448,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 57.216109384642444,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 84
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 94,
          "capped_draws": 17,
          "coverage_status": "rated",
          "distinct_rated_opponents": 46,
          "draws": 17,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-opus-4-8",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 39,
          "model": "claude-opus-4-8",
          "point_rating_method": "sequential_elo",
          "public_id": "E-13ec9509bc80f2bf",
          "rated_matches": 94,
          "raw_elo_rating": 1470.264528764638,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 43.63359523406752,
          "uncertainty": 7.54891760425771,
          "unilateral_faults": 0,
          "wins": 38
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 116,
          "capped_draws": 14,
          "coverage_status": "rated",
          "distinct_rated_opponents": 58,
          "draws": 14,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-opus-5",
            "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-25T15:48:00Z",
          "losses": 41,
          "model": "claude-opus-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-0437af9582860271",
          "rated_matches": 116,
          "raw_elo_rating": 1600.2178597089212,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 57.178073203245866,
          "uncertainty": 2.4750163521024238,
          "unilateral_faults": 0,
          "wins": 61
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 94,
          "capped_draws": 5,
          "coverage_status": "rated",
          "distinct_rated_opponents": 47,
          "draws": 5,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-opus-5",
            "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-25T15:48:00Z",
          "losses": 23,
          "model": "claude-opus-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-93a6875407c22137",
          "rated_matches": 94,
          "raw_elo_rating": 1810.8029618970652,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 78.05140670041531,
          "uncertainty": 7.54891760425771,
          "unilateral_faults": 0,
          "wins": 66
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 98,
          "capped_draws": 10,
          "coverage_status": "rated",
          "distinct_rated_opponents": 47,
          "draws": 10,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-sonnet-5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 39,
          "model": "claude-sonnet-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-cd50a27a6bb44b58",
          "rated_matches": 98,
          "raw_elo_rating": 1525.1532485760156,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 49.265789786658594,
          "uncertainty": 6.501890762960602,
          "unilateral_faults": 0,
          "wins": 49
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 89,
          "capped_draws": 19,
          "coverage_status": "rated",
          "distinct_rated_opponents": 43,
          "draws": 19,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-sonnet-5",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 41,
          "model": "claude-sonnet-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-d1a3c0549627f78e",
          "rated_matches": 89,
          "raw_elo_rating": 1444.200355658939,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 40.88566173777684,
          "uncertainty": 8.954627669472988,
          "unilateral_faults": 0,
          "wins": 29
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 76,
          "capped_draws": 26,
          "coverage_status": "rated",
          "distinct_rated_opponents": 38,
          "draws": 26,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "deepseek/deepseek-v4-flash",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T06:10:40Z",
          "losses": 43,
          "model": "deepseek/deepseek-v4-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-f1d9dfb787d0d902",
          "rated_matches": 76,
          "raw_elo_rating": 1160.6408625081874,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "repaired",
          "score": 11.880934761298485,
          "uncertainty": 13.230288229818967,
          "unilateral_faults": 0,
          "wins": 7
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 76,
          "capped_draws": 13,
          "coverage_status": "rated",
          "distinct_rated_opponents": 38,
          "draws": 13,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "deepseek/deepseek-v4-flash",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-01T00:15:48Z",
          "losses": 39,
          "model": "deepseek/deepseek-v4-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-fd9da5310ad15cac",
          "rated_matches": 76,
          "raw_elo_rating": 1561.0748409852954,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 52.35231723983702,
          "uncertainty": 13.230288229818967,
          "unilateral_faults": 0,
          "wins": 24
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 104,
          "capped_draws": 44,
          "coverage_status": "rated",
          "distinct_rated_opponents": 51,
          "draws": 44,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "google/gemini-3.1-flash-lite",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 38,
          "model": "google/gemini-3.1-flash-lite",
          "point_rating_method": "sequential_elo",
          "public_id": "E-7669b8a03ef19548",
          "rated_matches": 104,
          "raw_elo_rating": 1442.0722052107417,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "repaired",
          "score": 40.98668493442913,
          "uncertainty": 5.045003647426665,
          "unilateral_faults": 0,
          "wins": 22
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 90,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 44,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "google/gemini-3.5-flash",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 11,
          "model": "google/gemini-3.5-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-22f31826bcf76511",
          "rated_matches": 88,
          "raw_elo_rating": 1899.4210224251667,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "repaired",
          "score": 86.87039539493097,
          "uncertainty": 9.249894000318006,
          "unilateral_faults": 0,
          "wins": 77
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 144,
          "capped_draws": 24,
          "coverage_status": "rated",
          "distinct_rated_opponents": 52,
          "draws": 24,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "google/gemini-3.5-flash-lite",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 67,
          "model": "google/gemini-3.5-flash-lite",
          "point_rating_method": "sequential_elo",
          "public_id": "E-4b4f303670ce9fb6",
          "rated_matches": 144,
          "raw_elo_rating": 1442.9189216381337,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 41.66026073492735,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 53
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 222,
          "capped_draws": 49,
          "coverage_status": "rated",
          "distinct_rated_opponents": 90,
          "draws": 49,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "google/gemini-3.5-flash-lite",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 88,
          "model": "google/gemini-3.5-flash-lite",
          "point_rating_method": "sequential_elo",
          "public_id": "E-77d8df8cd762fd09",
          "rated_matches": 222,
          "raw_elo_rating": 1407.613568595336,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 38.74208683227142,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 85
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 156,
          "capped_draws": 97,
          "coverage_status": "rated",
          "distinct_rated_opponents": 61,
          "draws": 97,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "google/gemini-3.6-flash",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 33,
          "model": "google/gemini-3.6-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-27590b9ddebe06e6",
          "rated_matches": 156,
          "raw_elo_rating": 1460.350057347287,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 43.552860190190096,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 26
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 100,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 50,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "google/gemini-3.6-flash",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 11,
          "model": "google/gemini-3.6-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-7484f4e7d8863a3b",
          "rated_matches": 100,
          "raw_elo_rating": 1993.5082608374075,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 96.6422998270312,
          "uncertainty": 6.001859510499461,
          "unilateral_faults": 0,
          "wins": 89
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 94,
          "capped_draws": 17,
          "coverage_status": "rated",
          "distinct_rated_opponents": 45,
          "draws": 17,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 55,
          "model": "gpt-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-adee794ecd761044",
          "rated_matches": 94,
          "raw_elo_rating": 1257.9362460272719,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 22.173830070391556,
          "uncertainty": 7.54891760425771,
          "unilateral_faults": 0,
          "wins": 22
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 86,
          "capped_draws": 19,
          "coverage_status": "rated",
          "distinct_rated_opponents": 42,
          "draws": 19,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.4",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 16,
          "model": "gpt-5.4",
          "point_rating_method": "sequential_elo",
          "public_id": "E-586de6c9939561c3",
          "rated_matches": 84,
          "raw_elo_rating": 1711.1296538562067,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 67.7403406860563,
          "uncertainty": 10.482614454664043,
          "unilateral_faults": 2,
          "wins": 49
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 94,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 43,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.4",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 1,
          "model": "gpt-5.4",
          "point_rating_method": "sequential_elo",
          "public_id": "E-d4fa7dbb9458c464",
          "rated_matches": 94,
          "raw_elo_rating": 2027.9678324469994,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 100.0,
          "uncertainty": 7.54891760425771,
          "unilateral_faults": 0,
          "wins": 93
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 100,
          "capped_draws": 4,
          "coverage_status": "rated",
          "distinct_rated_opponents": 48,
          "draws": 4,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.4-mini",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 39,
          "model": "gpt-5.4-mini",
          "point_rating_method": "sequential_elo",
          "public_id": "E-62424dfd649cbac9",
          "rated_matches": 98,
          "raw_elo_rating": 1628.750407707507,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 59.73623054906832,
          "uncertainty": 6.501890762960602,
          "unilateral_faults": 2,
          "wins": 55
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 108,
          "capped_draws": 22,
          "coverage_status": "rated",
          "distinct_rated_opponents": 52,
          "draws": 22,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.4-nano",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 55,
          "model": "gpt-5.4-nano",
          "point_rating_method": "sequential_elo",
          "public_id": "E-9257cc1e94bf4b17",
          "rated_matches": 108,
          "raw_elo_rating": 1308.066198532366,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 27.51592622364584,
          "uncertainty": 4.1413142610575715,
          "unilateral_faults": 0,
          "wins": 31
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 82,
          "capped_draws": 4,
          "coverage_status": "rated",
          "distinct_rated_opponents": 40,
          "draws": 4,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.4-nano",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-09T17:30:50Z",
          "losses": 74,
          "model": "gpt-5.4-nano",
          "point_rating_method": "sequential_elo",
          "public_id": "E-c48c1aed1cdecc72",
          "rated_matches": 80,
          "raw_elo_rating": 1041.9481369055254,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "repaired",
          "score": 0.0,
          "uncertainty": 11.805555555555554,
          "unilateral_faults": 2,
          "wins": 2
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 108,
          "capped_draws": 65,
          "coverage_status": "rated",
          "distinct_rated_opponents": 53,
          "draws": 65,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 14,
          "model": "gpt-5.5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-e4496be687faac9d",
          "rated_matches": 108,
          "raw_elo_rating": 1625.1613317167532,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "repaired",
          "score": 59.564351449683706,
          "uncertainty": 4.1413142610575715,
          "unilateral_faults": 0,
          "wins": 29
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 90,
          "capped_draws": 9,
          "coverage_status": "rated",
          "distinct_rated_opponents": 44,
          "draws": 9,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.6-luna",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-10T05:30:29Z",
          "losses": 29,
          "model": "gpt-5.6-luna",
          "point_rating_method": "sequential_elo",
          "public_id": "E-4f775a5b7b265dae",
          "rated_matches": 90,
          "raw_elo_rating": 1681.7158247375462,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 64.91454480895466,
          "uncertainty": 8.664241836095918,
          "unilateral_faults": 0,
          "wins": 52
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 91,
          "capped_draws": 13,
          "coverage_status": "rated",
          "distinct_rated_opponents": 44,
          "draws": 13,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.6-luna",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 39,
          "model": "gpt-5.6-luna",
          "point_rating_method": "sequential_elo",
          "public_id": "E-87b37ed5ff73def5",
          "rated_matches": 91,
          "raw_elo_rating": 1553.3629268180623,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "repaired",
          "score": 51.96516648339348,
          "uncertainty": 8.378603514268699,
          "unilateral_faults": 0,
          "wins": 39
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 92,
          "capped_draws": 21,
          "coverage_status": "rated",
          "distinct_rated_opponents": 42,
          "draws": 21,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.6-sol",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 23,
          "model": "gpt-5.6-sol",
          "point_rating_method": "sequential_elo",
          "public_id": "E-544e51eb5e949386",
          "rated_matches": 92,
          "raw_elo_rating": 1644.1561281370252,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 61.164248353993486,
          "uncertainty": 8.09758473652126,
          "unilateral_faults": 0,
          "wins": 48
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 100,
          "capped_draws": 1,
          "coverage_status": "rated",
          "distinct_rated_opponents": 50,
          "draws": 1,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.6-sol",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-10T05:30:29Z",
          "losses": 37,
          "model": "gpt-5.6-sol",
          "point_rating_method": "sequential_elo",
          "public_id": "E-bc834303cebba06a",
          "rated_matches": 100,
          "raw_elo_rating": 1661.0108027125154,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 63.03718007148168,
          "uncertainty": 6.001859510499461,
          "unilateral_faults": 0,
          "wins": 62
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 98,
          "capped_draws": 34,
          "coverage_status": "rated",
          "distinct_rated_opponents": 47,
          "draws": 34,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.6-terra",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-10T05:30:29Z",
          "losses": 31,
          "model": "gpt-5.6-terra",
          "point_rating_method": "sequential_elo",
          "public_id": "E-46de264ad4571b48",
          "rated_matches": 98,
          "raw_elo_rating": 1468.1014264525709,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "repaired",
          "score": 43.49963047361349,
          "uncertainty": 6.501890762960602,
          "unilateral_faults": 0,
          "wins": 33
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 32,
          "capped_draws": 8,
          "coverage_status": "rated",
          "distinct_rated_opponents": 15,
          "draws": 8,
          "evaluated_setting_identity": {
            "canonical_provider_route": "unknown_legacy",
            "effective_request_value": "enabled",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "inclusionai/ling-3.0-flash:free",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 19,
          "model": "inclusionai/ling-3.0-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-dd34dd6c69ef6a73",
          "rated_matches": 30,
          "raw_elo_rating": 1343.2896596270887,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "enabled",
          "repair_status": "first_pass",
          "score": 27.68717636213546,
          "uncertainty": 46.05265101338746,
          "unilateral_faults": 0,
          "wins": 3
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 88,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 42,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "meta/muse-spark-1.2",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-08-13T16:58:34Z",
          "losses": 12,
          "model": "meta/muse-spark-1.2",
          "point_rating_method": "sequential_elo",
          "public_id": "E-052cdf1e5975b860",
          "rated_matches": 88,
          "raw_elo_rating": 1832.923348449229,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 80.14955515143204,
          "uncertainty": 9.249894000318006,
          "unilateral_faults": 0,
          "wins": 76
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 102,
          "capped_draws": 7,
          "coverage_status": "rated",
          "distinct_rated_opponents": 48,
          "draws": 7,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "enabled",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "minimax/minimax-m3",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 68,
          "model": "minimax/minimax-m3",
          "point_rating_method": "sequential_elo",
          "public_id": "E-e0a841a9daa66219",
          "rated_matches": 102,
          "raw_elo_rating": 1293.2880278495784,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "enabled",
          "repair_status": "repaired",
          "score": 25.911126435305174,
          "uncertainty": 5.516463908214657,
          "unilateral_faults": 0,
          "wins": 27
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 106,
          "capped_draws": 4,
          "coverage_status": "rated",
          "distinct_rated_opponents": 52,
          "draws": 4,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "enabled",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "moonshotai/kimi-k2.7-code",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 51,
          "model": "moonshotai/kimi-k2.7-code",
          "point_rating_method": "sequential_elo",
          "public_id": "E-4935e918b1e70ea1",
          "rated_matches": 106,
          "raw_elo_rating": 1457.399910028884,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "enabled",
          "repair_status": "repaired",
          "score": 42.57288379544755,
          "uncertainty": 4.586824452283178,
          "unilateral_faults": 0,
          "wins": 51
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 145,
          "capped_draws": 16,
          "coverage_status": "rated",
          "distinct_rated_opponents": 54,
          "draws": 16,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "moonshotai/kimi-k3",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T14:00:00Z",
          "losses": 48,
          "model": "moonshotai/kimi-k3",
          "point_rating_method": "sequential_elo",
          "public_id": "E-58aadd759ee9fa72",
          "rated_matches": 136,
          "raw_elo_rating": 1694.6446506662096,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "first_pass",
          "score": 67.00524526280067,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 72
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 96,
          "capped_draws": 20,
          "coverage_status": "rated",
          "distinct_rated_opponents": 47,
          "draws": 20,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "nvidia/nemotron-3-ultra-550b-a55b",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 36,
          "model": "nvidia/nemotron-3-ultra-550b-a55b",
          "point_rating_method": "sequential_elo",
          "public_id": "E-b851008baae8f441",
          "rated_matches": 96,
          "raw_elo_rating": 1528.1057891742366,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "repaired",
          "score": 49.52252542484147,
          "uncertainty": 7.017308256680951,
          "unilateral_faults": 0,
          "wins": 40
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 98,
          "capped_draws": 17,
          "coverage_status": "rated",
          "distinct_rated_opponents": 49,
          "draws": 17,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "o3",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 46,
          "model": "o3",
          "point_rating_method": "sequential_elo",
          "public_id": "E-428923c2eb87dc7a",
          "rated_matches": 98,
          "raw_elo_rating": 1468.681575830985,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 43.55826547626181,
          "uncertainty": 6.501890762960602,
          "unilateral_faults": 0,
          "wins": 35
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 94,
          "capped_draws": 24,
          "coverage_status": "rated",
          "distinct_rated_opponents": 47,
          "draws": 24,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "openai/gpt-oss-120b",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 43,
          "model": "openai/gpt-oss-120b",
          "point_rating_method": "sequential_elo",
          "public_id": "E-a3e0c8f8ea39b5ec",
          "rated_matches": 94,
          "raw_elo_rating": 1422.8019145344933,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "repaired",
          "score": 38.83660567477785,
          "uncertainty": 7.54891760425771,
          "unilateral_faults": 0,
          "wins": 27
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 160,
          "capped_draws": 28,
          "coverage_status": "rated",
          "distinct_rated_opponents": 58,
          "draws": 28,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "enabled",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "poolside/laguna-s-2.1",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 74,
          "model": "poolside/laguna-s-2.1",
          "point_rating_method": "sequential_elo",
          "public_id": "E-ffd72d2c5c11728a",
          "rated_matches": 160,
          "raw_elo_rating": 1415.0856930075604,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "enabled",
          "repair_status": "first_pass",
          "score": 39.01837754189059,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 58
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 96,
          "capped_draws": 30,
          "coverage_status": "rated",
          "distinct_rated_opponents": 46,
          "draws": 30,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "enabled",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "qwen/qwen3.7-max",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 54,
          "model": "qwen/qwen3.7-max",
          "point_rating_method": "sequential_elo",
          "public_id": "E-24581eb49b81bf8f",
          "rated_matches": 96,
          "raw_elo_rating": 1196.0815382797539,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "enabled",
          "repair_status": "repaired",
          "score": 15.965232157159793,
          "uncertainty": 7.017308256680951,
          "unilateral_faults": 0,
          "wins": 12
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 100,
          "capped_draws": 18,
          "coverage_status": "rated",
          "distinct_rated_opponents": 49,
          "draws": 18,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "enabled",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "qwen/qwen3.7-plus",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 42,
          "model": "qwen/qwen3.7-plus",
          "point_rating_method": "sequential_elo",
          "public_id": "E-1e5dceaf2ba3ca9a",
          "rated_matches": 100,
          "raw_elo_rating": 1513.515357215152,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "enabled",
          "repair_status": "repaired",
          "score": 48.12999209690405,
          "uncertainty": 6.001859510499461,
          "unilateral_faults": 0,
          "wins": 40
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 16,
          "capped_draws": 5,
          "coverage_status": "under_covered",
          "distinct_rated_opponents": 10,
          "draws": 5,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "qwen/qwen3.8-max",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 4,
          "model": "qwen/qwen3.8-max",
          "point_rating_method": "sequential_elo",
          "public_id": "E-ef3bbb2ff5470c0f",
          "rated_matches": 16,
          "raw_elo_rating": 1500.3453591301432,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 41.01649081370751,
          "uncertainty": 77.5178125181665,
          "unilateral_faults": 0,
          "wins": 7
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 14,
          "capped_draws": 2,
          "coverage_status": "rated",
          "distinct_rated_opponents": 7,
          "draws": 2,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "stealth/ox-alpha",
            "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-08-22T00:27:26Z",
          "losses": 2,
          "model": "stealth/ox-alpha",
          "point_rating_method": "sequential_elo",
          "public_id": "E-c6a1445bccefbe07",
          "rated_matches": 14,
          "raw_elo_rating": 1586.795907182653,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "repaired",
          "score": 49.120717176476376,
          "uncertainty": 85.34944487358055,
          "unilateral_faults": 0,
          "wins": 10
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 14,
          "capped_draws": 1,
          "coverage_status": "rated",
          "distinct_rated_opponents": 7,
          "draws": 1,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "stealth/ox-alpha",
            "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-08-22T00:27:26Z",
          "losses": 8,
          "model": "stealth/ox-alpha",
          "point_rating_method": "sequential_elo",
          "public_id": "E-d28e485f395cbca4",
          "rated_matches": 14,
          "raw_elo_rating": 1474.0444126130988,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "first_pass",
          "score": 37.72505869837807,
          "uncertainty": 85.34944487358055,
          "unilateral_faults": 0,
          "wins": 5
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 138,
          "capped_draws": 35,
          "coverage_status": "rated",
          "distinct_rated_opponents": 52,
          "draws": 35,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "thinkingmachines/inkling",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 76,
          "model": "thinkingmachines/inkling",
          "point_rating_method": "sequential_elo",
          "public_id": "E-46c7f693daaae605",
          "rated_matches": 138,
          "raw_elo_rating": 1359.3433979275337,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 33.14168798272348,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 27
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 20,
          "capped_draws": 3,
          "coverage_status": "under_covered",
          "distinct_rated_opponents": 9,
          "draws": 3,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "thinkingmachines/inkling-small",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 15,
          "model": "thinkingmachines/inkling-small",
          "point_rating_method": "sequential_elo",
          "public_id": "E-53de0c492cdf9f2f",
          "rated_matches": 20,
          "raw_elo_rating": 1346.7122318417303,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 26.47208042284504,
          "uncertainty": 65.3589451179962,
          "unilateral_faults": 0,
          "wins": 2
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 104,
          "capped_draws": 8,
          "coverage_status": "rated",
          "distinct_rated_opponents": 51,
          "draws": 8,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "x-ai/grok-4.5",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T14:00:00Z",
          "losses": 21,
          "model": "x-ai/grok-4.5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-d709aeb6802f9289",
          "rated_matches": 102,
          "raw_elo_rating": 1777.1699941075071,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 74.81649706686221,
          "uncertainty": 5.516463908214657,
          "unilateral_faults": 2,
          "wins": 73
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 108,
          "capped_draws": 23,
          "coverage_status": "rated",
          "distinct_rated_opponents": 49,
          "draws": 23,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "enabled",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "x-ai/grok-build-0.1",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 43,
          "model": "x-ai/grok-build-0.1",
          "point_rating_method": "sequential_elo",
          "public_id": "E-f1ded648f3ab17dc",
          "rated_matches": 108,
          "raw_elo_rating": 1483.761287066289,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "enabled",
          "repair_status": "repaired",
          "score": 45.273218336317015,
          "uncertainty": 4.1413142610575715,
          "unilateral_faults": 0,
          "wins": 42
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 110,
          "capped_draws": 3,
          "coverage_status": "rated",
          "distinct_rated_opponents": 50,
          "draws": 3,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "enabled",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "xiaomi/mimo-v2.5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 60,
          "model": "xiaomi/mimo-v2.5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-1208f50b0908ecb4",
          "rated_matches": 110,
          "raw_elo_rating": 1280.781906067578,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "enabled",
          "repair_status": "repaired",
          "score": 24.79337921651107,
          "uncertainty": 3.707899787624953,
          "unilateral_faults": 0,
          "wins": 47
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 102,
          "capped_draws": 16,
          "coverage_status": "rated",
          "distinct_rated_opponents": 48,
          "draws": 16,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "xiaomi/mimo-v2.5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T06:10:40Z",
          "losses": 56,
          "model": "xiaomi/mimo-v2.5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-2a71bee21bd7c0b9",
          "rated_matches": 102,
          "raw_elo_rating": 1405.5069647830076,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "repaired",
          "score": 37.25295995113266,
          "uncertainty": 5.516463908214657,
          "unilateral_faults": 0,
          "wins": 30
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 80,
          "capped_draws": 7,
          "coverage_status": "rated",
          "distinct_rated_opponents": 40,
          "draws": 7,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "z-ai/glm-5.2",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-11T17:22:09Z",
          "losses": 30,
          "model": "z-ai/glm-5.2",
          "point_rating_method": "sequential_elo",
          "public_id": "E-f889d782e3cce209",
          "rated_matches": 80,
          "raw_elo_rating": 1437.7540280999642,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "repaired",
          "score": 40.0036272413998,
          "uncertainty": 11.805555555555554,
          "unilateral_faults": 0,
          "wins": 43
        }
      ],
      "GB2-02": [
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 80,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 37,
          "draws": 31,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-fable-5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 9,
          "model": "claude-fable-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-cd3608270e8c00fd",
          "rated_matches": 78,
          "raw_elo_rating": 1685.6539281264988,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 68.84186917568367,
          "uncertainty": 12.5043950463012,
          "unilateral_faults": 2,
          "wins": 38
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 138,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 54,
          "draws": 125,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-opus-4-5",
            "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 11,
          "model": "claude-opus-4-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-03472a04778e9928",
          "rated_matches": 138,
          "raw_elo_rating": 1466.4846616121374,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 22.143649514386354,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 2
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 0,
          "capped_draws": 0,
          "coverage_status": "pending",
          "distinct_rated_opponents": 0,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "legacy_shared_thinking_budget",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-opus-4-5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "budget",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 0,
          "model": "claude-opus-4-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-3cbd11fb314c75e1",
          "rated_matches": 0,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "budget",
          "reasoning_setting": "legacy_shared_thinking_budget",
          "repair_status": "first_pass",
          "unilateral_faults": 0,
          "wins": 0
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 78,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 39,
          "draws": 72,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-opus-4-8",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 5,
          "model": "claude-opus-4-8",
          "point_rating_method": "sequential_elo",
          "public_id": "E-ed71c4ecf219b609",
          "rated_matches": 78,
          "raw_elo_rating": 1451.7183503047993,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 16.344385607773184,
          "uncertainty": 12.5043950463012,
          "unilateral_faults": 0,
          "wins": 1
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 76,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 38,
          "draws": 32,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-opus-5",
            "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-25T10:50:00Z",
          "losses": 9,
          "model": "claude-opus-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-50b401cafe71e710",
          "rated_matches": 76,
          "raw_elo_rating": 1657.8362240629167,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 62.46897998868618,
          "uncertainty": 13.230288229818967,
          "unilateral_faults": 0,
          "wins": 35
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 76,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 38,
          "draws": 36,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-opus-5",
            "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-25T10:50:00Z",
          "losses": 7,
          "model": "claude-opus-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-8a5bf2e23121edf6",
          "rated_matches": 76,
          "raw_elo_rating": 1647.1115742963248,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 60.0622613093993,
          "uncertainty": 13.230288229818967,
          "unilateral_faults": 0,
          "wins": 33
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 62,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 30,
          "draws": 55,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-sonnet-5",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 3,
          "model": "claude-sonnet-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-874db7679e1f7332",
          "rated_matches": 62,
          "raw_elo_rating": 1511.2971744001827,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 28.504507698976763,
          "uncertainty": 19.244078834871203,
          "unilateral_faults": 0,
          "wins": 4
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 78,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 36,
          "draws": 73,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-sonnet-5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 4,
          "model": "claude-sonnet-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-a1a16bb5799cfdbe",
          "rated_matches": 78,
          "raw_elo_rating": 1476.5961079238732,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 21.927203253446606,
          "uncertainty": 12.5043950463012,
          "unilateral_faults": 0,
          "wins": 1
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 66,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 33,
          "draws": 55,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "deepseek/deepseek-v4-flash",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T06:10:40Z",
          "losses": 11,
          "model": "deepseek/deepseek-v4-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-08e2baea96c43eb4",
          "rated_matches": 66,
          "raw_elo_rating": 1431.814073892673,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 11.010487913026688,
          "uncertainty": 17.33472217815261,
          "unilateral_faults": 0,
          "wins": 0
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 70,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 35,
          "draws": 59,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "deepseek/deepseek-v4-flash",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-01T00:15:48Z",
          "losses": 9,
          "model": "deepseek/deepseek-v4-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-1e168b9e73c26073",
          "rated_matches": 70,
          "raw_elo_rating": 1483.118399769498,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "repaired",
          "score": 22.83708293329852,
          "uncertainty": 15.58908290969266,
          "unilateral_faults": 0,
          "wins": 2
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 94,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 47,
          "draws": 74,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "google/gemini-3.5-flash",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 10,
          "model": "google/gemini-3.5-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-ef7a835bdb46a90e",
          "rated_matches": 94,
          "raw_elo_rating": 1490.007826929545,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "repaired",
          "score": 25.82657411049858,
          "uncertainty": 7.54891760425771,
          "unilateral_faults": 0,
          "wins": 10
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 107,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 41,
          "draws": 105,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "google/gemini-3.5-flash-lite",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 2,
          "model": "google/gemini-3.5-flash-lite",
          "point_rating_method": "sequential_elo",
          "public_id": "E-dbbc5835674b5f2c",
          "rated_matches": 107,
          "raw_elo_rating": 1472.044979547752,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 22.367578645782174,
          "uncertainty": 4.362522432468809,
          "unilateral_faults": 0,
          "wins": 0
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 88,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 44,
          "draws": 82,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "google/gemini-3.6-flash",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 5,
          "model": "google/gemini-3.6-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-62275b0c39dda32a",
          "rated_matches": 88,
          "raw_elo_rating": 1448.5362643626052,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 16.214567763911244,
          "uncertainty": 9.249894000318006,
          "unilateral_faults": 0,
          "wins": 1
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 77,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 34,
          "draws": 68,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.4",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 4,
          "model": "gpt-5.4",
          "point_rating_method": "sequential_elo",
          "public_id": "E-67423a89b95a1aba",
          "rated_matches": 77,
          "raw_elo_rating": 1493.0766723506626,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 25.561074219037017,
          "uncertainty": 12.86385170722978,
          "unilateral_faults": 0,
          "wins": 5
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 82,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 40,
          "draws": 70,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.4",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 8,
          "model": "gpt-5.4",
          "point_rating_method": "sequential_elo",
          "public_id": "E-f4948a32cdd115a9",
          "rated_matches": 82,
          "raw_elo_rating": 1463.1177660210396,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 19.148888518137927,
          "uncertainty": 11.132129994845172,
          "unilateral_faults": 0,
          "wins": 4
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 90,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 43,
          "draws": 84,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.4-mini",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 3,
          "model": "gpt-5.4-mini",
          "point_rating_method": "sequential_elo",
          "public_id": "E-6724998b59176607",
          "rated_matches": 90,
          "raw_elo_rating": 1472.1832965878284,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 21.626339283900553,
          "uncertainty": 8.664241836095918,
          "unilateral_faults": 0,
          "wins": 3
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 80,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 38,
          "draws": 77,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.4-nano",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 3,
          "model": "gpt-5.4-nano",
          "point_rating_method": "sequential_elo",
          "public_id": "E-d96eaa4f1d20c47b",
          "rated_matches": 80,
          "raw_elo_rating": 1475.7131921870432,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "repaired",
          "score": 21.854529388279282,
          "uncertainty": 11.805555555555554,
          "unilateral_faults": 0,
          "wins": 0
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 74,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 37,
          "draws": 45,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 9,
          "model": "gpt-5.5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-8460841e3919c568",
          "rated_matches": 74,
          "raw_elo_rating": 1576.1121672722809,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 43.99378748372811,
          "uncertainty": 13.985026918962571,
          "unilateral_faults": 0,
          "wins": 20
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 66,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 30,
          "draws": 63,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.6-luna",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 2,
          "model": "gpt-5.6-luna",
          "point_rating_method": "sequential_elo",
          "public_id": "E-2f3ae5ed2aa83217",
          "rated_matches": 66,
          "raw_elo_rating": 1515.1687546699268,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 29.716112021846637,
          "uncertainty": 17.33472217815261,
          "unilateral_faults": 0,
          "wins": 1
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 72,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 36,
          "draws": 66,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.6-luna",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-10T05:30:29Z",
          "losses": 6,
          "model": "gpt-5.6-luna",
          "point_rating_method": "sequential_elo",
          "public_id": "E-e2dda893ae4363f2",
          "rated_matches": 72,
          "raw_elo_rating": 1467.7463855821793,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 19.534394534685426,
          "uncertainty": 14.770573598065289,
          "unilateral_faults": 0,
          "wins": 0
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 78,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 39,
          "draws": 39,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.6-sol",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-10T05:30:29Z",
          "losses": 12,
          "model": "gpt-5.6-sol",
          "point_rating_method": "sequential_elo",
          "public_id": "E-087d760c91df7f17",
          "rated_matches": 78,
          "raw_elo_rating": 1581.8188124317824,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "repaired",
          "score": 45.54023061897745,
          "uncertainty": 12.5043950463012,
          "unilateral_faults": 0,
          "wins": 27
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 68,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 30,
          "draws": 40,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.6-sol",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 1,
          "model": "gpt-5.6-sol",
          "point_rating_method": "sequential_elo",
          "public_id": "E-1d0646e1538c1b7a",
          "rated_matches": 68,
          "raw_elo_rating": 1623.7312204453247,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 54.238717509734094,
          "uncertainty": 16.4429265428846,
          "unilateral_faults": 0,
          "wins": 27
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 86,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 42,
          "draws": 76,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.6-terra",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-10T05:30:29Z",
          "losses": 9,
          "model": "gpt-5.6-terra",
          "point_rating_method": "sequential_elo",
          "public_id": "E-82ad98d8d570daab",
          "rated_matches": 86,
          "raw_elo_rating": 1492.4957620772557,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "repaired",
          "score": 25.970772760443374,
          "uncertainty": 9.855626741889738,
          "unilateral_faults": 0,
          "wins": 1
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 22,
          "capped_draws": 0,
          "coverage_status": "under_covered",
          "distinct_rated_opponents": 11,
          "draws": 18,
          "evaluated_setting_identity": {
            "canonical_provider_route": "unknown_legacy",
            "effective_request_value": "enabled",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "inclusionai/ling-3.0-flash:free",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 4,
          "model": "inclusionai/ling-3.0-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-129026c5e53b35ad",
          "rated_matches": 22,
          "raw_elo_rating": 1438.7847701679702,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "enabled",
          "repair_status": "repaired",
          "score": 4.824111939258095,
          "uncertainty": 60.5072070285374,
          "unilateral_faults": 0,
          "wins": 0
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 106,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 41,
          "draws": 101,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "enabled",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "meituan/longcat-2.0",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 3,
          "model": "meituan/longcat-2.0",
          "point_rating_method": "sequential_elo",
          "public_id": "E-a00d8e3eb7dd07cf",
          "rated_matches": 106,
          "raw_elo_rating": 1476.8316916886058,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "enabled",
          "repair_status": "repaired",
          "score": 23.401496235109175,
          "uncertainty": 4.586824452283178,
          "unilateral_faults": 0,
          "wins": 2
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 67,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 31,
          "draws": 50,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "meta/muse-spark-1.2",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-08-13T16:58:34Z",
          "losses": 6,
          "model": "meta/muse-spark-1.2",
          "point_rating_method": "sequential_elo",
          "public_id": "E-2b12f5618349c056",
          "rated_matches": 67,
          "raw_elo_rating": 1509.5573026507243,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 28.53778014221482,
          "uncertainty": 16.883906259083243,
          "unilateral_faults": 0,
          "wins": 11
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 86,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 39,
          "draws": 71,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "enabled",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "minimax/minimax-m3",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 14,
          "model": "minimax/minimax-m3",
          "point_rating_method": "sequential_elo",
          "public_id": "E-cad87bcb23d33fef",
          "rated_matches": 86,
          "raw_elo_rating": 1429.2739821056432,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "enabled",
          "repair_status": "repaired",
          "score": 11.783172968660383,
          "uncertainty": 9.855626741889738,
          "unilateral_faults": 0,
          "wins": 1
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 118,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 56,
          "draws": 91,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "enabled",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "moonshotai/kimi-k2.7-code",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 23,
          "model": "moonshotai/kimi-k2.7-code",
          "point_rating_method": "sequential_elo",
          "public_id": "E-85c8a9372a607001",
          "rated_matches": 118,
          "raw_elo_rating": 1474.596618403244,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "enabled",
          "repair_status": "repaired",
          "score": 23.349084470138546,
          "uncertainty": 2.084924851410568,
          "unilateral_faults": 0,
          "wins": 4
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 104,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 39,
          "draws": 79,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "moonshotai/kimi-k3",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T14:00:00Z",
          "losses": 18,
          "model": "moonshotai/kimi-k3",
          "point_rating_method": "sequential_elo",
          "public_id": "E-0c4144684fc36307",
          "rated_matches": 104,
          "raw_elo_rating": 1460.9653251764248,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "first_pass",
          "score": 19.758668893473487,
          "uncertainty": 5.045003647426665,
          "unilateral_faults": 0,
          "wins": 7
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 90,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 44,
          "draws": 84,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "nvidia/nemotron-3-ultra-550b-a55b",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 5,
          "model": "nvidia/nemotron-3-ultra-550b-a55b",
          "point_rating_method": "sequential_elo",
          "public_id": "E-bd70ebbd81fdbef0",
          "rated_matches": 90,
          "raw_elo_rating": 1453.1606606288503,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "repaired",
          "score": 17.357469503708607,
          "uncertainty": 8.664241836095918,
          "unilateral_faults": 0,
          "wins": 1
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 86,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 42,
          "draws": 77,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "openai/gpt-oss-120b",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 5,
          "model": "openai/gpt-oss-120b",
          "point_rating_method": "sequential_elo",
          "public_id": "E-8f0c6569aa132f8e",
          "rated_matches": 86,
          "raw_elo_rating": 1473.9362990217546,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 21.805843612607568,
          "uncertainty": 9.855626741889738,
          "unilateral_faults": 0,
          "wins": 4
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 118,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 41,
          "draws": 112,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "enabled",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "poolside/laguna-s-2.1",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 4,
          "model": "poolside/laguna-s-2.1",
          "point_rating_method": "sequential_elo",
          "public_id": "E-7164ee63b9dd911a",
          "rated_matches": 116,
          "raw_elo_rating": 1468.6265515338287,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "enabled",
          "repair_status": "first_pass",
          "score": 21.9393094022954,
          "uncertainty": 2.4750163521024238,
          "unilateral_faults": 0,
          "wins": 0
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 118,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 44,
          "draws": 113,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "enabled",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "poolside/laguna-s-2.1",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 5,
          "model": "poolside/laguna-s-2.1",
          "point_rating_method": "sequential_elo",
          "public_id": "E-ba56689188a301b2",
          "rated_matches": 118,
          "raw_elo_rating": 1461.650267468705,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "enabled",
          "repair_status": "repaired",
          "score": 20.443793826539274,
          "uncertainty": 2.084924851410568,
          "unilateral_faults": 0,
          "wins": 0
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 100,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 48,
          "draws": 83,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "enabled",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "qwen/qwen3.7-max",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 13,
          "model": "qwen/qwen3.7-max",
          "point_rating_method": "sequential_elo",
          "public_id": "E-95265340f8562bfd",
          "rated_matches": 100,
          "raw_elo_rating": 1462.125463708624,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "enabled",
          "repair_status": "repaired",
          "score": 19.847233163024622,
          "uncertainty": 6.001859510499461,
          "unilateral_faults": 0,
          "wins": 4
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 86,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 39,
          "draws": 81,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "enabled",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "qwen/qwen3.7-plus",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 4,
          "model": "qwen/qwen3.7-plus",
          "point_rating_method": "sequential_elo",
          "public_id": "E-57293d5b71f14882",
          "rated_matches": 86,
          "raw_elo_rating": 1480.3725891120614,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "enabled",
          "repair_status": "repaired",
          "score": 23.250211486876427,
          "uncertainty": 9.855626741889738,
          "unilateral_faults": 0,
          "wins": 1
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 20,
          "capped_draws": 0,
          "coverage_status": "under_covered",
          "distinct_rated_opponents": 10,
          "draws": 18,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "qwen/qwen3.8-max",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 2,
          "model": "qwen/qwen3.8-max",
          "point_rating_method": "sequential_elo",
          "public_id": "E-7ca9241c6a1cf54f",
          "rated_matches": 20,
          "raw_elo_rating": 1473.6963543985923,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 11.78759779354171,
          "uncertainty": 65.3589451179962,
          "unilateral_faults": 0,
          "wins": 0
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 14,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 7,
          "draws": 8,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "stealth/ox-alpha",
            "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-08-22T00:27:26Z",
          "losses": 2,
          "model": "stealth/ox-alpha",
          "point_rating_method": "sequential_elo",
          "public_id": "E-427d180a6aa40aa2",
          "rated_matches": 14,
          "raw_elo_rating": 1521.106547069262,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "first_pass",
          "score": 18.838064764369765,
          "uncertainty": 85.34944487358055,
          "unilateral_faults": 0,
          "wins": 4
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 14,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 7,
          "draws": 9,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "stealth/ox-alpha",
            "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-08-22T00:27:26Z",
          "losses": 3,
          "model": "stealth/ox-alpha",
          "point_rating_method": "sequential_elo",
          "public_id": "E-8ad03916301062ed",
          "rated_matches": 14,
          "raw_elo_rating": 1488.2202220411896,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "first_pass",
          "score": 11.458044487650438,
          "uncertainty": 85.34944487358055,
          "unilateral_faults": 0,
          "wins": 2
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 14,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 7,
          "draws": 7,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "stealth/ox-alpha",
            "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-08-22T00:27:26Z",
          "losses": 6,
          "model": "stealth/ox-alpha",
          "point_rating_method": "sequential_elo",
          "public_id": "E-b4db3ddedfd59608",
          "rated_matches": 14,
          "raw_elo_rating": 1437.161693598434,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "first_pass",
          "score": 0.0,
          "uncertainty": 85.34944487358055,
          "unilateral_faults": 0,
          "wins": 1
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 86,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 41,
          "draws": 76,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "stepfun/step-3.7-flash",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 9,
          "model": "stepfun/step-3.7-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-0ccea44addccfff0",
          "rated_matches": 86,
          "raw_elo_rating": 1478.1857236712685,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "repaired",
          "score": 22.759457008176497,
          "uncertainty": 9.855626741889738,
          "unilateral_faults": 0,
          "wins": 1
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 20,
          "capped_draws": 0,
          "coverage_status": "under_covered",
          "distinct_rated_opponents": 11,
          "draws": 20,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "thinkingmachines/inkling-small",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 0,
          "model": "thinkingmachines/inkling-small",
          "point_rating_method": "sequential_elo",
          "public_id": "E-647caf2136958821",
          "rated_matches": 20,
          "raw_elo_rating": 1484.2472717904682,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "repaired",
          "score": 14.155329190210882,
          "uncertainty": 65.3589451179962,
          "unilateral_faults": 0,
          "wins": 0
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 98,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 49,
          "draws": 69,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "x-ai/grok-4.5",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T14:00:00Z",
          "losses": 16,
          "model": "x-ai/grok-4.5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-da5ea0258e71b6ab",
          "rated_matches": 98,
          "raw_elo_rating": 1492.6220047983245,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 26.601192408895606,
          "uncertainty": 6.501890762960602,
          "unilateral_faults": 0,
          "wins": 13
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 92,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 44,
          "draws": 86,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "enabled",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "x-ai/grok-build-0.1",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 3,
          "model": "x-ai/grok-build-0.1",
          "point_rating_method": "sequential_elo",
          "public_id": "E-99592fa0331c6679",
          "rated_matches": 92,
          "raw_elo_rating": 1471.922484272434,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "enabled",
          "repair_status": "repaired",
          "score": 21.669541208427077,
          "uncertainty": 8.09758473652126,
          "unilateral_faults": 0,
          "wins": 3
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 90,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 41,
          "draws": 75,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "enabled",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "xiaomi/mimo-v2.5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 11,
          "model": "xiaomi/mimo-v2.5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-5b213ae773e821cc",
          "rated_matches": 90,
          "raw_elo_rating": 1489.18525311898,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "enabled",
          "repair_status": "repaired",
          "score": 25.441748388952313,
          "uncertainty": 8.664241836095918,
          "unilateral_faults": 0,
          "wins": 4
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 80,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 37,
          "draws": 76,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "xiaomi/mimo-v2.5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-01T00:15:48Z",
          "losses": 4,
          "model": "xiaomi/mimo-v2.5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-a5f372b0e5962ee5",
          "rated_matches": 80,
          "raw_elo_rating": 1460.0313175143754,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "repaired",
          "score": 18.335359856187495,
          "uncertainty": 11.805555555555554,
          "unilateral_faults": 0,
          "wins": 0
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 88,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 41,
          "draws": 77,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "xiaomi/mimo-v2.5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T06:10:40Z",
          "losses": 6,
          "model": "xiaomi/mimo-v2.5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-c37f25e181320efb",
          "rated_matches": 88,
          "raw_elo_rating": 1479.0790665127915,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "repaired",
          "score": 23.06867806610496,
          "uncertainty": 9.249894000318006,
          "unilateral_faults": 0,
          "wins": 5
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 64,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 32,
          "draws": 63,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "z-ai/glm-5.2",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-11T17:22:09Z",
          "losses": 1,
          "model": "z-ai/glm-5.2",
          "point_rating_method": "sequential_elo",
          "public_id": "E-32435b01ac08ed41",
          "rated_matches": 64,
          "raw_elo_rating": 1468.1999436475344,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "repaired",
          "score": 19.008405115879473,
          "uncertainty": 18.26736729460423,
          "unilateral_faults": 0,
          "wins": 0
        }
      ],
      "GB2-03": [
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 0,
          "capped_draws": 0,
          "coverage_status": "pending",
          "distinct_rated_opponents": 0,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "legacy_shared_thinking_budget",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-opus-4-5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "budget",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 0,
          "model": "claude-opus-4-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-cef4890e88806969",
          "rated_matches": 0,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "budget",
          "reasoning_setting": "legacy_shared_thinking_budget",
          "repair_status": "first_pass",
          "unilateral_faults": 0,
          "wins": 0
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 160,
          "capped_draws": 19,
          "coverage_status": "rated",
          "distinct_rated_opponents": 58,
          "draws": 77,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-opus-4-5",
            "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 48,
          "model": "claude-opus-4-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-dfb18dba94eee30b",
          "rated_matches": 160,
          "raw_elo_rating": 1498.8789320043286,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 47.38893238646811,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 35
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 64,
          "capped_draws": 7,
          "coverage_status": "rated",
          "distinct_rated_opponents": 32,
          "draws": 38,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-opus-4-8",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 15,
          "model": "claude-opus-4-8",
          "point_rating_method": "sequential_elo",
          "public_id": "E-823b961281482cd1",
          "rated_matches": 64,
          "raw_elo_rating": 1445.7477631553459,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 37.68653930194108,
          "uncertainty": 18.26736729460423,
          "unilateral_faults": 0,
          "wins": 11
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 80,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 40,
          "draws": 4,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-opus-5",
            "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-25T15:48:00Z",
          "losses": 10,
          "model": "claude-opus-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-bd02f4c2907d0a7c",
          "rated_matches": 80,
          "raw_elo_rating": 1847.6520197765583,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 93.14221553912532,
          "uncertainty": 11.805555555555554,
          "unilateral_faults": 0,
          "wins": 66
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 82,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 41,
          "draws": 4,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-opus-5",
            "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-25T15:48:00Z",
          "losses": 5,
          "model": "claude-opus-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-d8babc5495b1a188",
          "rated_matches": 82,
          "raw_elo_rating": 1888.0062822581406,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 98.71307186653274,
          "uncertainty": 11.132129994845172,
          "unilateral_faults": 0,
          "wins": 73
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 90,
          "capped_draws": 8,
          "coverage_status": "rated",
          "distinct_rated_opponents": 42,
          "draws": 31,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-sonnet-5",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 36,
          "model": "claude-sonnet-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-db41eba0d9c3a185",
          "rated_matches": 90,
          "raw_elo_rating": 1455.2008449551374,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 40.02092072410418,
          "uncertainty": 8.664241836095918,
          "unilateral_faults": 0,
          "wins": 23
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 32,
          "capped_draws": 1,
          "coverage_status": "rated",
          "distinct_rated_opponents": 16,
          "draws": 16,
          "evaluated_setting_identity": {
            "canonical_provider_route": "unknown_legacy",
            "effective_request_value": "enabled",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "cohere/north-mini-code:free",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 13,
          "model": "cohere/north-mini-code",
          "point_rating_method": "sequential_elo",
          "public_id": "E-0f669ae82234cf76",
          "rated_matches": 32,
          "raw_elo_rating": 1393.6082077811413,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "enabled",
          "repair_status": "repaired",
          "score": 27.856624323434982,
          "uncertainty": 43.288827977848925,
          "unilateral_faults": 0,
          "wins": 3
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 54,
          "capped_draws": 1,
          "coverage_status": "rated",
          "distinct_rated_opponents": 27,
          "draws": 18,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "deepseek/deepseek-v4-flash",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-01T00:15:48Z",
          "losses": 21,
          "model": "deepseek/deepseek-v4-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-32e04fe5ad231857",
          "rated_matches": 54,
          "raw_elo_rating": 1523.0961019109775,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 47.63490899953319,
          "uncertainty": 23.66998624632421,
          "unilateral_faults": 0,
          "wins": 15
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 68,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 34,
          "draws": 30,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "google/gemini-3.5-flash",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 15,
          "model": "google/gemini-3.5-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-8ed795ea8fd1e0aa",
          "rated_matches": 68,
          "raw_elo_rating": 1577.6092570519809,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "repaired",
          "score": 55.84887374161656,
          "uncertainty": 16.4429265428846,
          "unilateral_faults": 0,
          "wins": 23
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 141,
          "capped_draws": 5,
          "coverage_status": "rated",
          "distinct_rated_opponents": 52,
          "draws": 49,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "google/gemini-3.5-flash-lite",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 59,
          "model": "google/gemini-3.5-flash-lite",
          "point_rating_method": "sequential_elo",
          "public_id": "E-c7e8525629d5d658",
          "rated_matches": 141,
          "raw_elo_rating": 1453.6481623860886,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 40.94884587514523,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 33
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 140,
          "capped_draws": 17,
          "coverage_status": "rated",
          "distinct_rated_opponents": 51,
          "draws": 70,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "google/gemini-3.5-flash-lite",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 50,
          "model": "google/gemini-3.5-flash-lite",
          "point_rating_method": "sequential_elo",
          "public_id": "E-d9a1854998f1794f",
          "rated_matches": 140,
          "raw_elo_rating": 1412.3489003818981,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 35.30645765084414,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 20
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 137,
          "capped_draws": 5,
          "coverage_status": "rated",
          "distinct_rated_opponents": 51,
          "draws": 40,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "google/gemini-3.6-flash",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 35,
          "model": "google/gemini-3.6-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-1d4a922c11c37a8d",
          "rated_matches": 137,
          "raw_elo_rating": 1593.388026886988,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 59.91981623001038,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 62
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 133,
          "capped_draws": 1,
          "coverage_status": "rated",
          "distinct_rated_opponents": 55,
          "draws": 29,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "google/gemini-3.6-flash",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 78,
          "model": "google/gemini-3.6-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-2e4f025f94dafe33",
          "rated_matches": 133,
          "raw_elo_rating": 1403.3327657948776,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 33.95985144610179,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 26
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 64,
          "capped_draws": 1,
          "coverage_status": "rated",
          "distinct_rated_opponents": 31,
          "draws": 35,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 19,
          "model": "gpt-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-e724ba162431d43a",
          "rated_matches": 64,
          "raw_elo_rating": 1402.0902606081052,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 31.739075020104682,
          "uncertainty": 18.26736729460423,
          "unilateral_faults": 0,
          "wins": 10
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 82,
          "capped_draws": 2,
          "coverage_status": "rated",
          "distinct_rated_opponents": 41,
          "draws": 38,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.4",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 25,
          "model": "gpt-5.4",
          "point_rating_method": "sequential_elo",
          "public_id": "E-496f83ad0bd69447",
          "rated_matches": 82,
          "raw_elo_rating": 1430.6751894818985,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 36.41082871103601,
          "uncertainty": 11.132129994845172,
          "unilateral_faults": 0,
          "wins": 19
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 94,
          "capped_draws": 6,
          "coverage_status": "rated",
          "distinct_rated_opponents": 42,
          "draws": 48,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.4",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 26,
          "model": "gpt-5.4",
          "point_rating_method": "sequential_elo",
          "public_id": "E-c535d0dba39ffdb8",
          "rated_matches": 94,
          "raw_elo_rating": 1465.4947162156686,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 41.54480799633329,
          "uncertainty": 7.54891760425771,
          "unilateral_faults": 0,
          "wins": 20
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 85,
          "capped_draws": 12,
          "coverage_status": "rated",
          "distinct_rated_opponents": 42,
          "draws": 49,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.4-mini",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 21,
          "model": "gpt-5.4-mini",
          "point_rating_method": "sequential_elo",
          "public_id": "E-9e39bdd48b7328c7",
          "rated_matches": 85,
          "raw_elo_rating": 1480.1394784776523,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "repaired",
          "score": 43.25460249709266,
          "uncertainty": 10.16638660171921,
          "unilateral_faults": 0,
          "wins": 15
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 76,
          "capped_draws": 7,
          "coverage_status": "rated",
          "distinct_rated_opponents": 38,
          "draws": 37,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 24,
          "model": "gpt-5.5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-c002b0ea38b845f8",
          "rated_matches": 76,
          "raw_elo_rating": 1436.9850240219848,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 37.041752080817375,
          "uncertainty": 13.230288229818967,
          "unilateral_faults": 0,
          "wins": 15
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 74,
          "capped_draws": 13,
          "coverage_status": "rated",
          "distinct_rated_opponents": 36,
          "draws": 44,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.6-luna",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-10T05:30:29Z",
          "losses": 17,
          "model": "gpt-5.6-luna",
          "point_rating_method": "sequential_elo",
          "public_id": "E-0300c20cb034e3a4",
          "rated_matches": 74,
          "raw_elo_rating": 1462.3304554695912,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 40.4123073013434,
          "uncertainty": 13.985026918962571,
          "unilateral_faults": 0,
          "wins": 13
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 93,
          "capped_draws": 3,
          "coverage_status": "rated",
          "distinct_rated_opponents": 43,
          "draws": 27,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.6-luna",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 44,
          "model": "gpt-5.6-luna",
          "point_rating_method": "sequential_elo",
          "public_id": "E-d4115a59dfe21984",
          "rated_matches": 93,
          "raw_elo_rating": 1441.308968688837,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 38.22032267709648,
          "uncertainty": 7.821062312939668,
          "unilateral_faults": 0,
          "wins": 22
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 90,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 42,
          "draws": 9,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.6-sol",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 25,
          "model": "gpt-5.6-sol",
          "point_rating_method": "sequential_elo",
          "public_id": "E-826bd7fcad40bd61",
          "rated_matches": 90,
          "raw_elo_rating": 1642.3853735340704,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 65.52108067097569,
          "uncertainty": 8.664241836095918,
          "unilateral_faults": 0,
          "wins": 56
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 60,
          "capped_draws": 2,
          "coverage_status": "rated",
          "distinct_rated_opponents": 30,
          "draws": 13,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.6-sol",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-10T05:30:29Z",
          "losses": 16,
          "model": "gpt-5.6-sol",
          "point_rating_method": "sequential_elo",
          "public_id": "E-b741de451c385e8e",
          "rated_matches": 60,
          "raw_elo_rating": 1556.5990433024108,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 52.56973107349277,
          "uncertainty": 20.268439966447993,
          "unilateral_faults": 0,
          "wins": 31
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 78,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 39,
          "draws": 39,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.6-terra",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-10T05:30:29Z",
          "losses": 25,
          "model": "gpt-5.6-terra",
          "point_rating_method": "sequential_elo",
          "public_id": "E-e44c62bb88a3042a",
          "rated_matches": 78,
          "raw_elo_rating": 1480.6473394621028,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 43.06898280210667,
          "uncertainty": 12.5043950463012,
          "unilateral_faults": 0,
          "wins": 14
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 142,
          "capped_draws": 19,
          "coverage_status": "rated",
          "distinct_rated_opponents": 50,
          "draws": 62,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "enabled",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "meituan/longcat-2.0",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 39,
          "model": "meituan/longcat-2.0",
          "point_rating_method": "sequential_elo",
          "public_id": "E-d3a5befe76215b48",
          "rated_matches": 142,
          "raw_elo_rating": 1476.9131306078064,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "enabled",
          "repair_status": "first_pass",
          "score": 44.134251044046394,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 41
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 94,
          "capped_draws": 8,
          "coverage_status": "rated",
          "distinct_rated_opponents": 43,
          "draws": 29,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "meta/muse-spark-1.2",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-08-13T16:58:34Z",
          "losses": 30,
          "model": "meta/muse-spark-1.2",
          "point_rating_method": "sequential_elo",
          "public_id": "E-4d97f32199e2a33d",
          "rated_matches": 94,
          "raw_elo_rating": 1547.3955110326083,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 52.70215835783597,
          "uncertainty": 7.54891760425771,
          "unilateral_faults": 0,
          "wins": 35
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 134,
          "capped_draws": 3,
          "coverage_status": "rated",
          "distinct_rated_opponents": 52,
          "draws": 52,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "moonshotai/kimi-k3",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T14:00:00Z",
          "losses": 21,
          "model": "moonshotai/kimi-k3",
          "point_rating_method": "sequential_elo",
          "public_id": "E-980b1f419104e27a",
          "rated_matches": 134,
          "raw_elo_rating": 1644.1494064849203,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "first_pass",
          "score": 66.78378455408968,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 61
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 76,
          "capped_draws": 5,
          "coverage_status": "rated",
          "distinct_rated_opponents": 35,
          "draws": 35,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "enabled",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "nex-agi/nex-n2-pro",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 27,
          "model": "nex-agi/nex-n2-pro",
          "point_rating_method": "sequential_elo",
          "public_id": "E-57ad2863cbf32d58",
          "rated_matches": 76,
          "raw_elo_rating": 1414.8192171011551,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "enabled",
          "repair_status": "repaired",
          "score": 34.022102828158765,
          "uncertainty": 13.230288229818967,
          "unilateral_faults": 0,
          "wins": 14
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 66,
          "capped_draws": 8,
          "coverage_status": "rated",
          "distinct_rated_opponents": 33,
          "draws": 43,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "openai/gpt-oss-120b",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 13,
          "model": "openai/gpt-oss-120b",
          "point_rating_method": "sequential_elo",
          "public_id": "E-87b4bd61da369b42",
          "rated_matches": 66,
          "raw_elo_rating": 1409.558557661116,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "repaired",
          "score": 32.858125032877226,
          "uncertainty": 17.33472217815261,
          "unilateral_faults": 0,
          "wins": 10
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 154,
          "capped_draws": 7,
          "coverage_status": "rated",
          "distinct_rated_opponents": 58,
          "draws": 87,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "enabled",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "poolside/laguna-s-2.1",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 50,
          "model": "poolside/laguna-s-2.1",
          "point_rating_method": "sequential_elo",
          "public_id": "E-08762a3df1a52f6b",
          "rated_matches": 154,
          "raw_elo_rating": 1404.8379963900634,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "enabled",
          "repair_status": "first_pass",
          "score": 34.49539831171606,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 17
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 164,
          "capped_draws": 17,
          "coverage_status": "rated",
          "distinct_rated_opponents": 59,
          "draws": 46,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "enabled",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "poolside/laguna-s-2.1",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 73,
          "model": "poolside/laguna-s-2.1",
          "point_rating_method": "sequential_elo",
          "public_id": "E-936fb7956df3d03b",
          "rated_matches": 164,
          "raw_elo_rating": 1409.001159135909,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "enabled",
          "repair_status": "repaired",
          "score": 35.19725261289695,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 45
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 16,
          "capped_draws": 1,
          "coverage_status": "under_covered",
          "distinct_rated_opponents": 9,
          "draws": 6,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "qwen/qwen3.8-max",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 5,
          "model": "qwen/qwen3.8-max",
          "point_rating_method": "sequential_elo",
          "public_id": "E-5481497913530d6b",
          "rated_matches": 16,
          "raw_elo_rating": 1501.4910334028175,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 38.823095003355,
          "uncertainty": 77.5178125181665,
          "unilateral_faults": 0,
          "wins": 5
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 0,
          "capped_draws": 0,
          "coverage_status": "pending",
          "distinct_rated_opponents": 0,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "stealth/ox-alpha",
            "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-08-21T22:22:23Z",
          "losses": 0,
          "model": "stealth/ox-alpha",
          "point_rating_method": "sequential_elo",
          "public_id": "E-01ad48d5f93e32a0",
          "rated_matches": 0,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "first_pass",
          "unilateral_faults": 0,
          "wins": 0
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 0,
          "capped_draws": 0,
          "coverage_status": "pending",
          "distinct_rated_opponents": 0,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "stealth/ox-alpha",
            "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-08-21T20:50:14Z",
          "losses": 0,
          "model": "stealth/ox-alpha",
          "point_rating_method": "sequential_elo",
          "public_id": "E-14673673976cc3eb",
          "rated_matches": 0,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "first_pass",
          "unilateral_faults": 0,
          "wins": 0
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 12,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 6,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "stealth/ox-alpha",
            "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-08-22T00:27:26Z",
          "losses": 1,
          "model": "stealth/ox-alpha",
          "point_rating_method": "sequential_elo",
          "public_id": "E-449a1a79eee8c26f",
          "rated_matches": 12,
          "raw_elo_rating": 1613.7046840011644,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "first_pass",
          "score": 52.212856458233006,
          "uncertainty": 94.92504905630729,
          "unilateral_faults": 0,
          "wins": 11
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 13,
          "capped_draws": 1,
          "coverage_status": "rated",
          "distinct_rated_opponents": 6,
          "draws": 5,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "stealth/ox-alpha",
            "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-08-22T00:27:26Z",
          "losses": 5,
          "model": "stealth/ox-alpha",
          "point_rating_method": "sequential_elo",
          "public_id": "E-7aeb7747204eb58b",
          "rated_matches": 12,
          "raw_elo_rating": 1461.1114825492753,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "first_pass",
          "score": 31.425075152965995,
          "uncertainty": 94.92504905630729,
          "unilateral_faults": 0,
          "wins": 2
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 0,
          "capped_draws": 0,
          "coverage_status": "pending",
          "distinct_rated_opponents": 0,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "stealth/ox-alpha",
            "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-08-21T20:50:14Z",
          "losses": 0,
          "model": "stealth/ox-alpha",
          "point_rating_method": "sequential_elo",
          "public_id": "E-7c7b61f033bf610f",
          "rated_matches": 0,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "repaired",
          "unilateral_faults": 0,
          "wins": 0
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 0,
          "capped_draws": 0,
          "coverage_status": "pending",
          "distinct_rated_opponents": 0,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "stealth/ox-alpha",
            "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-08-21T22:22:23Z",
          "losses": 0,
          "model": "stealth/ox-alpha",
          "point_rating_method": "sequential_elo",
          "public_id": "E-b1c61a0495f26448",
          "rated_matches": 0,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "first_pass",
          "unilateral_faults": 0,
          "wins": 0
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 0,
          "capped_draws": 0,
          "coverage_status": "pending",
          "distinct_rated_opponents": 0,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "stealth/ox-alpha",
            "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-08-21T22:22:23Z",
          "losses": 0,
          "model": "stealth/ox-alpha",
          "point_rating_method": "sequential_elo",
          "public_id": "E-d5879b5524510a71",
          "rated_matches": 0,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "first_pass",
          "unilateral_faults": 0,
          "wins": 0
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 134,
          "capped_draws": 3,
          "coverage_status": "rated",
          "distinct_rated_opponents": 51,
          "draws": 25,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "thinkingmachines/inkling",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 37,
          "model": "thinkingmachines/inkling",
          "point_rating_method": "sequential_elo",
          "public_id": "E-77829668b3641188",
          "rated_matches": 134,
          "raw_elo_rating": 1556.1129209687915,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 54.7905686677935,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 72
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 17,
          "capped_draws": 0,
          "coverage_status": "under_covered",
          "distinct_rated_opponents": 9,
          "draws": 6,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "thinkingmachines/inkling-small",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 5,
          "model": "thinkingmachines/inkling-small",
          "point_rating_method": "sequential_elo",
          "public_id": "E-a17a40d8dd4cbb06",
          "rated_matches": 17,
          "raw_elo_rating": 1509.8258524700977,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "repaired",
          "score": 40.330911797900164,
          "uncertainty": 74.10113019775793,
          "unilateral_faults": 0,
          "wins": 6
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 78,
          "capped_draws": 1,
          "coverage_status": "rated",
          "distinct_rated_opponents": 39,
          "draws": 28,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "x-ai/grok-4.5",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T14:00:00Z",
          "losses": 26,
          "model": "x-ai/grok-4.5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-cbed46472ce4dd05",
          "rated_matches": 78,
          "raw_elo_rating": 1508.9890080189186,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 46.92997006877206,
          "uncertainty": 12.5043950463012,
          "unilateral_faults": 0,
          "wins": 24
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 70,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 33,
          "draws": 32,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "enabled",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "x-ai/grok-build-0.1",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 20,
          "model": "x-ai/grok-build-0.1",
          "point_rating_method": "sequential_elo",
          "public_id": "E-2a93343a8a88fd59",
          "rated_matches": 70,
          "raw_elo_rating": 1411.5993597267618,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "enabled",
          "repair_status": "repaired",
          "score": 33.32639046166839,
          "uncertainty": 15.58908290969266,
          "unilateral_faults": 0,
          "wins": 18
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 54,
          "capped_draws": 15,
          "coverage_status": "rated",
          "distinct_rated_opponents": 27,
          "draws": 40,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "z-ai/glm-5.2",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-11T17:22:09Z",
          "losses": 11,
          "model": "z-ai/glm-5.2",
          "point_rating_method": "sequential_elo",
          "public_id": "E-40aa28533b1afda1",
          "rated_matches": 54,
          "raw_elo_rating": 1442.1124041249502,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "repaired",
          "score": 36.602494823476015,
          "uncertainty": 23.66998624632421,
          "unilateral_faults": 0,
          "wins": 3
        }
      ],
      "GB2-04": [
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 80,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 40,
          "draws": 33,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-fable-5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 17,
          "model": "claude-fable-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-eb1f17ce19beffd0",
          "rated_matches": 80,
          "raw_elo_rating": 1582.2001981056562,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 55.133363671974216,
          "uncertainty": 11.805555555555554,
          "unilateral_faults": 0,
          "wins": 30
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 0,
          "capped_draws": 0,
          "coverage_status": "pending",
          "distinct_rated_opponents": 0,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "legacy_shared_thinking_budget",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-opus-4-5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "budget",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 0,
          "model": "claude-opus-4-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-8c9e611d78967342",
          "rated_matches": 0,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "budget",
          "reasoning_setting": "legacy_shared_thinking_budget",
          "repair_status": "first_pass",
          "unilateral_faults": 0,
          "wins": 0
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 104,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 51,
          "draws": 76,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-opus-4-5",
            "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 16,
          "model": "claude-opus-4-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-cbae2963ded72d76",
          "rated_matches": 103,
          "raw_elo_rating": 1477.6181811749257,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 39.978937009585955,
          "uncertainty": 5.279033784546012,
          "unilateral_faults": 0,
          "wins": 11
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 104,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 49,
          "draws": 87,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-opus-4-8",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 12,
          "model": "claude-opus-4-8",
          "point_rating_method": "sequential_elo",
          "public_id": "E-caf91ab5b69b1e64",
          "rated_matches": 104,
          "raw_elo_rating": 1470.653364825019,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 38.94522426719343,
          "uncertainty": 5.045003647426665,
          "unilateral_faults": 0,
          "wins": 5
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 102,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 51,
          "draws": 54,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-opus-5",
            "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-25T15:48:00Z",
          "losses": 31,
          "model": "claude-opus-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-048d3dcf802043b4",
          "rated_matches": 102,
          "raw_elo_rating": 1555.643719772659,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 51.850357271156476,
          "uncertainty": 5.516463908214657,
          "unilateral_faults": 0,
          "wins": 17
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 104,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 52,
          "draws": 36,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-opus-5",
            "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-25T15:48:00Z",
          "losses": 26,
          "model": "claude-opus-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-d0f0a2b1c4bbddae",
          "rated_matches": 104,
          "raw_elo_rating": 1562.403382529865,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 52.93886080577703,
          "uncertainty": 5.045003647426665,
          "unilateral_faults": 0,
          "wins": 42
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 76,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 36,
          "draws": 46,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-sonnet-5",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 16,
          "model": "claude-sonnet-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-7031fd4afe7acb91",
          "rated_matches": 76,
          "raw_elo_rating": 1471.7287106223077,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 38.1105048676341,
          "uncertainty": 13.230288229818967,
          "unilateral_faults": 0,
          "wins": 14
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 102,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 49,
          "draws": 72,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-sonnet-5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 11,
          "model": "claude-sonnet-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-b1fc5b99a5deb881",
          "rated_matches": 102,
          "raw_elo_rating": 1482.2172580461772,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "repaired",
          "score": 40.6514142799952,
          "uncertainty": 5.516463908214657,
          "unilateral_faults": 0,
          "wins": 19
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 64,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 32,
          "draws": 50,
          "evaluated_setting_identity": {
            "canonical_provider_route": "unknown_legacy",
            "effective_request_value": "enabled",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "cohere/north-mini-code:free",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 11,
          "model": "cohere/north-mini-code",
          "point_rating_method": "sequential_elo",
          "public_id": "E-1460cf3cd86be35c",
          "rated_matches": 64,
          "raw_elo_rating": 1464.2346713769077,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "enabled",
          "repair_status": "repaired",
          "score": 36.352919328591064,
          "uncertainty": 18.26736729460423,
          "unilateral_faults": 0,
          "wins": 3
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 66,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 33,
          "draws": 53,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "deepseek/deepseek-v4-flash",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-01T00:15:48Z",
          "losses": 9,
          "model": "deepseek/deepseek-v4-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-5d143d6301429619",
          "rated_matches": 66,
          "raw_elo_rating": 1470.9778216962018,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 37.49517602497302,
          "uncertainty": 17.33472217815261,
          "unilateral_faults": 0,
          "wins": 4
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 92,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 43,
          "draws": 77,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "google/gemini-3.1-flash-lite",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 5,
          "model": "google/gemini-3.1-flash-lite",
          "point_rating_method": "sequential_elo",
          "public_id": "E-860c31323fa5eda7",
          "rated_matches": 90,
          "raw_elo_rating": 1494.6174746882057,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "repaired",
          "score": 42.15860784753806,
          "uncertainty": 8.664241836095918,
          "unilateral_faults": 2,
          "wins": 8
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 100,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 48,
          "draws": 57,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "google/gemini-3.5-flash",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 16,
          "model": "google/gemini-3.5-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-32cfa6c9dfb1d16f",
          "rated_matches": 100,
          "raw_elo_rating": 1552.5455372468282,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "repaired",
          "score": 51.31859933665385,
          "uncertainty": 6.001859510499461,
          "unilateral_faults": 0,
          "wins": 27
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 114,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 56,
          "draws": 86,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "google/gemini-3.5-flash-lite",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 15,
          "model": "google/gemini-3.5-flash-lite",
          "point_rating_method": "sequential_elo",
          "public_id": "E-5c270e2afa7b70f5",
          "rated_matches": 111,
          "raw_elo_rating": 1487.5247726522077,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 41.70749337777939,
          "uncertainty": 3.4955591261534025,
          "unilateral_faults": 0,
          "wins": 10
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 139,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 55,
          "draws": 109,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "google/gemini-3.5-flash-lite",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 16,
          "model": "google/gemini-3.5-flash-lite",
          "point_rating_method": "sequential_elo",
          "public_id": "E-6098de52ddfabfb1",
          "rated_matches": 133,
          "raw_elo_rating": 1443.188278257529,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 35.439751017064516,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 8
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 137,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 55,
          "draws": 102,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "google/gemini-3.6-flash",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 25,
          "model": "google/gemini-3.6-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-cefb1dec9ce36375",
          "rated_matches": 137,
          "raw_elo_rating": 1409.2508299046585,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 30.34058179495447,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 10
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 118,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 59,
          "draws": 86,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "google/gemini-3.6-flash",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 12,
          "model": "google/gemini-3.6-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-d109ab12db58a65f",
          "rated_matches": 118,
          "raw_elo_rating": 1491.0414684830237,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 42.41597592157571,
          "uncertainty": 2.084924851410568,
          "unilateral_faults": 0,
          "wins": 20
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 92,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 40,
          "draws": 75,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "enabled",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "google/gemma-4-31b-it",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 6,
          "model": "google/gemma-4-31b-it",
          "point_rating_method": "sequential_elo",
          "public_id": "E-62ca2464f2212fc9",
          "rated_matches": 90,
          "raw_elo_rating": 1463.0389711785886,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "enabled",
          "repair_status": "repaired",
          "score": 37.342280705591044,
          "uncertainty": 8.664241836095918,
          "unilateral_faults": 2,
          "wins": 9
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 100,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 48,
          "draws": 62,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 21,
          "model": "gpt-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-6f1aae863396df76",
          "rated_matches": 100,
          "raw_elo_rating": 1483.6589592065263,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 40.81207563674785,
          "uncertainty": 6.001859510499461,
          "unilateral_faults": 0,
          "wins": 17
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 102,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 49,
          "draws": 66,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.4",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 14,
          "model": "gpt-5.4",
          "point_rating_method": "sequential_elo",
          "public_id": "E-0b4132559ee98caf",
          "rated_matches": 102,
          "raw_elo_rating": 1505.7163572188297,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 44.235477379188055,
          "uncertainty": 5.516463908214657,
          "unilateral_faults": 0,
          "wins": 22
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 82,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 37,
          "draws": 41,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.4",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 33,
          "model": "gpt-5.4",
          "point_rating_method": "sequential_elo",
          "public_id": "E-cae96a5e03c2613e",
          "rated_matches": 82,
          "raw_elo_rating": 1395.4317548321806,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 26.729763986537332,
          "uncertainty": 11.132129994845172,
          "unilateral_faults": 0,
          "wins": 8
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 90,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 45,
          "draws": 61,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.4-mini",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 9,
          "model": "gpt-5.4-mini",
          "point_rating_method": "sequential_elo",
          "public_id": "E-74f5bcc8ad3796a5",
          "rated_matches": 90,
          "raw_elo_rating": 1559.7577793037303,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 52.09375303448146,
          "uncertainty": 8.664241836095918,
          "unilateral_faults": 0,
          "wins": 20
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 98,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 46,
          "draws": 64,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.4-nano",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-09T17:30:50Z",
          "losses": 9,
          "model": "gpt-5.4-nano",
          "point_rating_method": "sequential_elo",
          "public_id": "E-a32cb67d48c62b3b",
          "rated_matches": 98,
          "raw_elo_rating": 1562.2888242629197,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "repaired",
          "score": 52.743625903198904,
          "uncertainty": 6.501890762960602,
          "unilateral_faults": 0,
          "wins": 25
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 102,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 51,
          "draws": 63,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 17,
          "model": "gpt-5.5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-9e7bdad81107b7e4",
          "rated_matches": 102,
          "raw_elo_rating": 1475.5304118625747,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 39.63154205082826,
          "uncertainty": 5.516463908214657,
          "unilateral_faults": 0,
          "wins": 22
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 78,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 36,
          "draws": 58,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.6-luna",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 11,
          "model": "gpt-5.6-luna",
          "point_rating_method": "sequential_elo",
          "public_id": "E-3c11110e415436c3",
          "rated_matches": 78,
          "raw_elo_rating": 1445.8487821616854,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 34.25188976239682,
          "uncertainty": 12.5043950463012,
          "unilateral_faults": 0,
          "wins": 9
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 98,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 47,
          "draws": 87,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.6-luna",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-10T05:30:29Z",
          "losses": 5,
          "model": "gpt-5.6-luna",
          "point_rating_method": "sequential_elo",
          "public_id": "E-5389e160269f5ceb",
          "rated_matches": 98,
          "raw_elo_rating": 1494.8994434966728,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 42.465453488707176,
          "uncertainty": 6.501890762960602,
          "unilateral_faults": 0,
          "wins": 6
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 78,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 36,
          "draws": 11,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.6-sol",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 3,
          "model": "gpt-5.6-sol",
          "point_rating_method": "sequential_elo",
          "public_id": "E-7f8aa62c2a56b424",
          "rated_matches": 78,
          "raw_elo_rating": 1802.997606042514,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 88.72393191119036,
          "uncertainty": 12.5043950463012,
          "unilateral_faults": 0,
          "wins": 64
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 108,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 52,
          "draws": 86,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.6-sol",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-10T05:30:29Z",
          "losses": 6,
          "model": "gpt-5.6-sol",
          "point_rating_method": "sequential_elo",
          "public_id": "E-c81bf4d15f3d48f1",
          "rated_matches": 108,
          "raw_elo_rating": 1524.9887263647072,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 47.3426724694463,
          "uncertainty": 4.1413142610575715,
          "unilateral_faults": 0,
          "wins": 16
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 98,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 48,
          "draws": 76,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.6-terra",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-10T05:30:29Z",
          "losses": 9,
          "model": "gpt-5.6-terra",
          "point_rating_method": "sequential_elo",
          "public_id": "E-89c18d144e85d89f",
          "rated_matches": 98,
          "raw_elo_rating": 1510.6341572765252,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 44.865298973012386,
          "uncertainty": 6.501890762960602,
          "unilateral_faults": 0,
          "wins": 13
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 50,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 25,
          "draws": 36,
          "evaluated_setting_identity": {
            "canonical_provider_route": "unknown_legacy",
            "effective_request_value": "enabled",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "inclusionai/ling-3.0-flash:free",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 10,
          "model": "inclusionai/ling-3.0-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-20e94e7276184071",
          "rated_matches": 50,
          "raw_elo_rating": 1425.6994207944547,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "enabled",
          "repair_status": "repaired",
          "score": 29.499842559488023,
          "uncertainty": 26.264004201400486,
          "unilateral_faults": 0,
          "wins": 4
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 143,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 51,
          "draws": 60,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "enabled",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "meituan/longcat-2.0",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 46,
          "model": "meituan/longcat-2.0",
          "point_rating_method": "sequential_elo",
          "public_id": "E-4ccf296e55b59be3",
          "rated_matches": 120,
          "raw_elo_rating": 1321.5639506069945,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "enabled",
          "repair_status": "repaired",
          "score": 16.613817698425585,
          "uncertainty": 1.7045454545454586,
          "unilateral_faults": 23,
          "wins": 14
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 142,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 55,
          "draws": 93,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "enabled",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "meituan/longcat-2.0",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 44,
          "model": "meituan/longcat-2.0",
          "point_rating_method": "sequential_elo",
          "public_id": "E-9c9e87bb30b3cb99",
          "rated_matches": 142,
          "raw_elo_rating": 1352.2288317182251,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "enabled",
          "repair_status": "first_pass",
          "score": 21.735234055222836,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 5
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 76,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 36,
          "draws": 40,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "meta/muse-spark-1.2",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-08-13T16:58:34Z",
          "losses": 27,
          "model": "meta/muse-spark-1.2",
          "point_rating_method": "sequential_elo",
          "public_id": "E-57e6f935250459a2",
          "rated_matches": 76,
          "raw_elo_rating": 1411.1381799035316,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 28.86928741865205,
          "uncertainty": 13.230288229818967,
          "unilateral_faults": 0,
          "wins": 9
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 92,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 44,
          "draws": 76,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "enabled",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "minimax/minimax-m3",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 9,
          "model": "minimax/minimax-m3",
          "point_rating_method": "sequential_elo",
          "public_id": "E-c60620c3c72a6064",
          "rated_matches": 92,
          "raw_elo_rating": 1483.269501274785,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "enabled",
          "repair_status": "repaired",
          "score": 40.496965218840195,
          "uncertainty": 8.09758473652126,
          "unilateral_faults": 0,
          "wins": 7
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 102,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 49,
          "draws": 79,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "enabled",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "moonshotai/kimi-k2.7-code",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 15,
          "model": "moonshotai/kimi-k2.7-code",
          "point_rating_method": "sequential_elo",
          "public_id": "E-eb97811a38950c20",
          "rated_matches": 102,
          "raw_elo_rating": 1431.1215027312614,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "enabled",
          "repair_status": "repaired",
          "score": 32.85833209398961,
          "uncertainty": 5.516463908214657,
          "unilateral_faults": 0,
          "wins": 8
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 137,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 53,
          "draws": 94,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "moonshotai/kimi-k3",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T14:00:00Z",
          "losses": 17,
          "model": "moonshotai/kimi-k3",
          "point_rating_method": "sequential_elo",
          "public_id": "E-7c724729d138057b",
          "rated_matches": 133,
          "raw_elo_rating": 1483.9182974099629,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "first_pass",
          "score": 41.65185972817385,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 22
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 88,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 42,
          "draws": 67,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "o3",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 12,
          "model": "o3",
          "point_rating_method": "sequential_elo",
          "public_id": "E-7e92e17a121661f4",
          "rated_matches": 88,
          "raw_elo_rating": 1452.4224780953568,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 35.65160344774605,
          "uncertainty": 9.249894000318006,
          "unilateral_faults": 0,
          "wins": 9
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 96,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 46,
          "draws": 83,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "openai/gpt-oss-120b",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 11,
          "model": "openai/gpt-oss-120b",
          "point_rating_method": "sequential_elo",
          "public_id": "E-f1288f2abfdbbfe4",
          "rated_matches": 96,
          "raw_elo_rating": 1452.7004190221962,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "repaired",
          "score": 35.96640446666731,
          "uncertainty": 7.017308256680951,
          "unilateral_faults": 0,
          "wins": 2
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 152,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 59,
          "draws": 94,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "enabled",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "poolside/laguna-s-2.1",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 46,
          "model": "poolside/laguna-s-2.1",
          "point_rating_method": "sequential_elo",
          "public_id": "E-e996fd38983e3b7f",
          "rated_matches": 152,
          "raw_elo_rating": 1380.6694525948496,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "enabled",
          "repair_status": "repaired",
          "score": 26.24251380391939,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 12
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 106,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 47,
          "draws": 66,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "enabled",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "qwen/qwen3.7-max",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 23,
          "model": "qwen/qwen3.7-max",
          "point_rating_method": "sequential_elo",
          "public_id": "E-ea08328e287de1ad",
          "rated_matches": 106,
          "raw_elo_rating": 1490.791657928284,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "enabled",
          "repair_status": "first_pass",
          "score": 42.07260490289768,
          "uncertainty": 4.586824452283178,
          "unilateral_faults": 0,
          "wins": 17
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 16,
          "capped_draws": 0,
          "coverage_status": "under_covered",
          "distinct_rated_opponents": 8,
          "draws": 9,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "qwen/qwen3.8-max",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 4,
          "model": "qwen/qwen3.8-max",
          "point_rating_method": "sequential_elo",
          "public_id": "E-1f87c69eddf28f4e",
          "rated_matches": 16,
          "raw_elo_rating": 1475.637623633983,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 30.86262516391439,
          "uncertainty": 77.5178125181665,
          "unilateral_faults": 0,
          "wins": 3
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 16,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 8,
          "draws": 8,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "stealth/ox-alpha",
            "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-08-22T00:27:26Z",
          "losses": 2,
          "model": "stealth/ox-alpha",
          "point_rating_method": "sequential_elo",
          "public_id": "E-43ae1b9ca4bd7996",
          "rated_matches": 16,
          "raw_elo_rating": 1544.9767970254613,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "repaired",
          "score": 41.43817833108209,
          "uncertainty": 77.5178125181665,
          "unilateral_faults": 0,
          "wins": 6
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 16,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 8,
          "draws": 11,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "stealth/ox-alpha",
            "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-08-22T00:27:26Z",
          "losses": 3,
          "model": "stealth/ox-alpha",
          "point_rating_method": "sequential_elo",
          "public_id": "E-6139f660620fd73b",
          "rated_matches": 16,
          "raw_elo_rating": 1499.2139224856492,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "first_pass",
          "score": 34.45846269406692,
          "uncertainty": 77.5178125181665,
          "unilateral_faults": 0,
          "wins": 2
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 16,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 8,
          "draws": 11,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "stealth/ox-alpha",
            "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-08-22T00:27:26Z",
          "losses": 4,
          "model": "stealth/ox-alpha",
          "point_rating_method": "sequential_elo",
          "public_id": "E-be47453e36658247",
          "rated_matches": 16,
          "raw_elo_rating": 1465.4137098841509,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "first_pass",
          "score": 29.30328232566859,
          "uncertainty": 77.5178125181665,
          "unilateral_faults": 0,
          "wins": 1
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 98,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 47,
          "draws": 76,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "stepfun/step-3.7-flash",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 11,
          "model": "stepfun/step-3.7-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-25e56c6bfae33c62",
          "rated_matches": 98,
          "raw_elo_rating": 1518.32655258939,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "repaired",
          "score": 46.03853672066733,
          "uncertainty": 6.501890762960602,
          "unilateral_faults": 0,
          "wins": 11
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 120,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 46,
          "draws": 94,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "thinkingmachines/inkling",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 19,
          "model": "thinkingmachines/inkling",
          "point_rating_method": "sequential_elo",
          "public_id": "E-fce01db31ecf26d2",
          "rated_matches": 120,
          "raw_elo_rating": 1454.3921381611772,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 36.872662603409985,
          "uncertainty": 1.7045454545454586,
          "unilateral_faults": 0,
          "wins": 7
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 20,
          "capped_draws": 0,
          "coverage_status": "under_covered",
          "distinct_rated_opponents": 10,
          "draws": 13,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "thinkingmachines/inkling-small",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 5,
          "model": "thinkingmachines/inkling-small",
          "point_rating_method": "sequential_elo",
          "public_id": "E-20d371c6aae692a2",
          "rated_matches": 20,
          "raw_elo_rating": 1469.3700914144779,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "repaired",
          "score": 31.39027464270986,
          "uncertainty": 65.3589451179962,
          "unilateral_faults": 0,
          "wins": 2
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 110,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 54,
          "draws": 82,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "x-ai/grok-4.5",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T14:00:00Z",
          "losses": 16,
          "model": "x-ai/grok-4.5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-ba6a8e6d7fc9a48d",
          "rated_matches": 110,
          "raw_elo_rating": 1479.3694583369315,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 40.43774279100727,
          "uncertainty": 3.707899787624953,
          "unilateral_faults": 0,
          "wins": 12
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 96,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 46,
          "draws": 84,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "enabled",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "x-ai/grok-build-0.1",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 7,
          "model": "x-ai/grok-build-0.1",
          "point_rating_method": "sequential_elo",
          "public_id": "E-85934b32572399da",
          "rated_matches": 96,
          "raw_elo_rating": 1480.7467967975713,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "enabled",
          "repair_status": "repaired",
          "score": 40.244014723647986,
          "uncertainty": 7.017308256680951,
          "unilateral_faults": 0,
          "wins": 5
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 90,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 42,
          "draws": 64,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "xiaomi/mimo-v2.5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T06:10:40Z",
          "losses": 19,
          "model": "xiaomi/mimo-v2.5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-00e6914e513b1656",
          "rated_matches": 90,
          "raw_elo_rating": 1465.9648732385099,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "repaired",
          "score": 37.78853685897672,
          "uncertainty": 8.664241836095918,
          "unilateral_faults": 0,
          "wins": 7
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 96,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 45,
          "draws": 65,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "xiaomi/mimo-v2.5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-01T00:15:48Z",
          "losses": 26,
          "model": "xiaomi/mimo-v2.5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-23e877112cb95491",
          "rated_matches": 96,
          "raw_elo_rating": 1454.1533586667938,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "repaired",
          "score": 36.18800561517503,
          "uncertainty": 7.017308256680951,
          "unilateral_faults": 0,
          "wins": 5
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 106,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 47,
          "draws": 90,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "enabled",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "xiaomi/mimo-v2.5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 12,
          "model": "xiaomi/mimo-v2.5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-2f7e15b8aa123825",
          "rated_matches": 106,
          "raw_elo_rating": 1474.3257249175822,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "enabled",
          "repair_status": "repaired",
          "score": 39.56123446848897,
          "uncertainty": 4.586824452283178,
          "unilateral_faults": 0,
          "wins": 4
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 96,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 46,
          "draws": 51,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "enabled",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "xiaomi/mimo-v2.5-pro",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 23,
          "model": "xiaomi/mimo-v2.5-pro",
          "point_rating_method": "sequential_elo",
          "public_id": "E-ffdebde8a72ed049",
          "rated_matches": 96,
          "raw_elo_rating": 1566.3530638646457,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "enabled",
          "repair_status": "repaired",
          "score": 53.300611514890754,
          "uncertainty": 7.017308256680951,
          "unilateral_faults": 0,
          "wins": 22
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 66,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 33,
          "draws": 49,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "z-ai/glm-5.2",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-11T17:22:09Z",
          "losses": 10,
          "model": "z-ai/glm-5.2",
          "point_rating_method": "sequential_elo",
          "public_id": "E-912f31ad14c4bf0a",
          "rated_matches": 66,
          "raw_elo_rating": 1489.7254504864673,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "repaired",
          "score": 40.35454880564338,
          "uncertainty": 17.33472217815261,
          "unilateral_faults": 0,
          "wins": 7
        }
      ],
      "GB2-05": [
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 106,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 53,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-fable-5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 42,
          "model": "claude-fable-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-ad7cf41c05ec3f64",
          "rated_matches": 106,
          "raw_elo_rating": 1679.6354629058385,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 62.71165398791373,
          "uncertainty": 4.586824452283178,
          "unilateral_faults": 0,
          "wins": 64
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 200,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 75,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-opus-4-5",
            "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 91,
          "model": "claude-opus-4-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-a75e9d71efa4a6bc",
          "rated_matches": 200,
          "raw_elo_rating": 1557.6899839620967,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 53.45354337379487,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 109
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 0,
          "capped_draws": 0,
          "coverage_status": "pending",
          "distinct_rated_opponents": 0,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "legacy_shared_thinking_budget",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-opus-4-5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "budget",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 0,
          "model": "claude-opus-4-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-ff0722d17402bafa",
          "rated_matches": 0,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "budget",
          "reasoning_setting": "legacy_shared_thinking_budget",
          "repair_status": "first_pass",
          "unilateral_faults": 0,
          "wins": 0
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 122,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 59,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-opus-4-8",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 56,
          "model": "claude-opus-4-8",
          "point_rating_method": "sequential_elo",
          "public_id": "E-924d7e6ee41b562e",
          "rated_matches": 122,
          "raw_elo_rating": 1537.859169314774,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 51.154684162643335,
          "uncertainty": 1.3334817333716131,
          "unilateral_faults": 0,
          "wins": 66
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 114,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 57,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-opus-5",
            "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-25T10:50:00Z",
          "losses": 18,
          "model": "claude-opus-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-32c377b229530444",
          "rated_matches": 114,
          "raw_elo_rating": 1881.8264374761118,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 79.61528545204392,
          "uncertainty": 2.875240412015687,
          "unilateral_faults": 0,
          "wins": 96
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 112,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 56,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-opus-5",
            "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-25T10:50:00Z",
          "losses": 10,
          "model": "claude-opus-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-d7111b534ebcaba2",
          "rated_matches": 112,
          "raw_elo_rating": 1969.491951088303,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 86.86773451101418,
          "uncertainty": 3.286043419179858,
          "unilateral_faults": 0,
          "wins": 102
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 92,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 44,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-sonnet-5",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 44,
          "model": "claude-sonnet-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-77d8a88f79b44f7d",
          "rated_matches": 92,
          "raw_elo_rating": 1481.5916885129375,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 46.03288300374409,
          "uncertainty": 8.09758473652126,
          "unilateral_faults": 0,
          "wins": 48
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 104,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 50,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-sonnet-5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 38,
          "model": "claude-sonnet-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-e0a09b1ea3f11175",
          "rated_matches": 104,
          "raw_elo_rating": 1590.3103541790922,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 55.263664052390155,
          "uncertainty": 5.045003647426665,
          "unilateral_faults": 0,
          "wins": 66
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 82,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 41,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "unknown_legacy",
            "effective_request_value": "enabled",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "cohere/north-mini-code:free",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 36,
          "model": "cohere/north-mini-code",
          "point_rating_method": "sequential_elo",
          "public_id": "E-a0518a43c688d1e2",
          "rated_matches": 82,
          "raw_elo_rating": 1552.4350508377818,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "enabled",
          "repair_status": "first_pass",
          "score": 51.714121198453974,
          "uncertainty": 11.132129994845172,
          "unilateral_faults": 0,
          "wins": 46
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 78,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 39,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "deepseek/deepseek-v4-flash",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-01T00:15:48Z",
          "losses": 48,
          "model": "deepseek/deepseek-v4-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-06a41d0e11b18b77",
          "rated_matches": 78,
          "raw_elo_rating": 1312.647194208838,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 31.710988307007685,
          "uncertainty": 12.5043950463012,
          "unilateral_faults": 0,
          "wins": 30
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 80,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 40,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "deepseek/deepseek-v4-flash",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T06:10:40Z",
          "losses": 45,
          "model": "deepseek/deepseek-v4-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-2c1cbd253f3a9d69",
          "rated_matches": 80,
          "raw_elo_rating": 1257.1871071905523,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 27.15201095688824,
          "uncertainty": 11.805555555555554,
          "unilateral_faults": 0,
          "wins": 35
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 98,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 49,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "google/gemini-3.1-flash-lite",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 70,
          "model": "google/gemini-3.1-flash-lite",
          "point_rating_method": "sequential_elo",
          "public_id": "E-7603462aff103041",
          "rated_matches": 98,
          "raw_elo_rating": 1196.77816581129,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "repaired",
          "score": 22.487988563537684,
          "uncertainty": 6.501890762960602,
          "unilateral_faults": 0,
          "wins": 28
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 112,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 56,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "google/gemini-3.5-flash",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 54,
          "model": "google/gemini-3.5-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-a7ce764239377b3f",
          "rated_matches": 112,
          "raw_elo_rating": 1553.2266000489765,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "repaired",
          "score": 52.301082285856566,
          "uncertainty": 3.286043419179858,
          "unilateral_faults": 0,
          "wins": 58
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 162,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 61,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "google/gemini-3.5-flash-lite",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 131,
          "model": "google/gemini-3.5-flash-lite",
          "point_rating_method": "sequential_elo",
          "public_id": "E-3dd83d6fa9f8f758",
          "rated_matches": 162,
          "raw_elo_rating": 1104.9629752879334,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 15.600315327273428,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 31
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 164,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 62,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "google/gemini-3.5-flash-lite",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 128,
          "model": "google/gemini-3.5-flash-lite",
          "point_rating_method": "sequential_elo",
          "public_id": "E-8826ab29e7591ece",
          "rated_matches": 164,
          "raw_elo_rating": 1126.374330356309,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 17.394128900976742,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 36
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 162,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 66,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "google/gemini-3.6-flash",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 7,
          "model": "google/gemini-3.6-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-5bcc61f900210bfa",
          "rated_matches": 162,
          "raw_elo_rating": 2029.54027540886,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 92.37716429814988,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 155
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 162,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 66,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "google/gemini-3.6-flash",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 75,
          "model": "google/gemini-3.6-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-d95a1da824d70f6d",
          "rated_matches": 162,
          "raw_elo_rating": 1510.5926868235526,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 49.28378462356395,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 87
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 124,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 57,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "enabled",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "google/gemma-4-31b-it",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 58,
          "model": "google/gemma-4-31b-it",
          "point_rating_method": "sequential_elo",
          "public_id": "E-fd1bc1e2e6ac48fb",
          "rated_matches": 124,
          "raw_elo_rating": 1583.880968834933,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "enabled",
          "repair_status": "repaired",
          "score": 55.00038838965367,
          "uncertainty": 0.9713595499957961,
          "unilateral_faults": 0,
          "wins": 66
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 102,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 51,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 52,
          "model": "gpt-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-9e5b308c41a36374",
          "rated_matches": 102,
          "raw_elo_rating": 1607.1651624106053,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 56.63196638824444,
          "uncertainty": 5.516463908214657,
          "unilateral_faults": 0,
          "wins": 50
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 96,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 44,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.4",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 17,
          "model": "gpt-5.4",
          "point_rating_method": "sequential_elo",
          "public_id": "E-34e3865fc087a754",
          "rated_matches": 96,
          "raw_elo_rating": 1843.4523646471466,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 76.15353884909591,
          "uncertainty": 7.017308256680951,
          "unilateral_faults": 0,
          "wins": 79
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 120,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 60,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.4",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 70,
          "model": "gpt-5.4",
          "point_rating_method": "sequential_elo",
          "public_id": "E-cafab3c275850d3b",
          "rated_matches": 120,
          "raw_elo_rating": 1461.6644809842144,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 44.802830877695115,
          "uncertainty": 1.7045454545454586,
          "unilateral_faults": 0,
          "wins": 50
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 124,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 58,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.4-mini",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 50,
          "model": "gpt-5.4-mini",
          "point_rating_method": "sequential_elo",
          "public_id": "E-0791f6b66243ec1a",
          "rated_matches": 124,
          "raw_elo_rating": 1576.1336146218378,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 54.357048515026754,
          "uncertainty": 0.9713595499957961,
          "unilateral_faults": 0,
          "wins": 74
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 92,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 46,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.4-nano",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 17,
          "model": "gpt-5.4-nano",
          "point_rating_method": "sequential_elo",
          "public_id": "E-8e40431df091d53f",
          "rated_matches": 92,
          "raw_elo_rating": 1819.1047661903833,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 74.05995071041148,
          "uncertainty": 8.09758473652126,
          "unilateral_faults": 0,
          "wins": 75
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 116,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 57,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.4-nano",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-09T17:30:50Z",
          "losses": 79,
          "model": "gpt-5.4-nano",
          "point_rating_method": "sequential_elo",
          "public_id": "E-a0d8c8fd6b01598c",
          "rated_matches": 116,
          "raw_elo_rating": 1253.3051649919003,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 27.449500663218604,
          "uncertainty": 2.4750163521024238,
          "unilateral_faults": 0,
          "wins": 37
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 98,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 49,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 31,
          "model": "gpt-5.5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-ffa82d1e96e897ab",
          "rated_matches": 98,
          "raw_elo_rating": 1717.6614023179375,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 65.742104336769,
          "uncertainty": 6.501890762960602,
          "unilateral_faults": 0,
          "wins": 67
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 93,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 44,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.6-luna",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 49,
          "model": "gpt-5.6-luna",
          "point_rating_method": "sequential_elo",
          "public_id": "E-8056d7cf3d4b6248",
          "rated_matches": 93,
          "raw_elo_rating": 1470.8329908962558,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 45.15785126150731,
          "uncertainty": 7.821062312939668,
          "unilateral_faults": 0,
          "wins": 44
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 116,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 58,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.6-luna",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-10T05:30:29Z",
          "losses": 59,
          "model": "gpt-5.6-luna",
          "point_rating_method": "sequential_elo",
          "public_id": "E-e917387a1c57aa23",
          "rated_matches": 116,
          "raw_elo_rating": 1602.8775455457373,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 56.477972228182814,
          "uncertainty": 2.4750163521024238,
          "unilateral_faults": 0,
          "wins": 57
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 94,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 44,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.6-sol",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 17,
          "model": "gpt-5.6-sol",
          "point_rating_method": "sequential_elo",
          "public_id": "E-c9acd4a3fb993f97",
          "rated_matches": 94,
          "raw_elo_rating": 1809.7744136870645,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 73.32160777460308,
          "uncertainty": 7.54891760425771,
          "unilateral_faults": 0,
          "wins": 77
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 98,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 49,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.6-sol",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-10T05:30:29Z",
          "losses": 37,
          "model": "gpt-5.6-sol",
          "point_rating_method": "sequential_elo",
          "public_id": "E-d61f8454991c5422",
          "rated_matches": 98,
          "raw_elo_rating": 1676.2772256568912,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 62.30556454623592,
          "uncertainty": 6.501890762960602,
          "unilateral_faults": 0,
          "wins": 61
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 110,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 52,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.6-terra",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-10T05:30:29Z",
          "losses": 45,
          "model": "gpt-5.6-terra",
          "point_rating_method": "sequential_elo",
          "public_id": "E-9664e98d37ece097",
          "rated_matches": 110,
          "raw_elo_rating": 1609.1466507381233,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 56.91665552510462,
          "uncertainty": 3.707899787624953,
          "unilateral_faults": 0,
          "wins": 65
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 172,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 62,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "enabled",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "meituan/longcat-2.0",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 60,
          "model": "meituan/longcat-2.0",
          "point_rating_method": "sequential_elo",
          "public_id": "E-73a7ad076eeaa6ae",
          "rated_matches": 172,
          "raw_elo_rating": 1665.397646233429,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "enabled",
          "repair_status": "first_pass",
          "score": 62.2150922209429,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 112
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 170,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 63,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "enabled",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "meituan/longcat-2.0",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 130,
          "model": "meituan/longcat-2.0",
          "point_rating_method": "sequential_elo",
          "public_id": "E-8b7eb63d4f53d846",
          "rated_matches": 170,
          "raw_elo_rating": 1167.4814201454985,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "enabled",
          "repair_status": "first_pass",
          "score": 20.85343047035033,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 40
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 94,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 44,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "meta/muse-spark-1.2",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-08-13T16:58:34Z",
          "losses": 41,
          "model": "meta/muse-spark-1.2",
          "point_rating_method": "sequential_elo",
          "public_id": "E-782ab5805e8c7fe1",
          "rated_matches": 94,
          "raw_elo_rating": 1554.8886887946508,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 52.15591097203426,
          "uncertainty": 7.54891760425771,
          "unilateral_faults": 0,
          "wins": 53
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 106,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 52,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "enabled",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "minimax/minimax-m3",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 103,
          "model": "minimax/minimax-m3",
          "point_rating_method": "sequential_elo",
          "public_id": "E-fb8ac45946e32e22",
          "rated_matches": 106,
          "raw_elo_rating": 924.4368254590598,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "enabled",
          "repair_status": "repaired",
          "score": 0.0,
          "uncertainty": 4.586824452283178,
          "unilateral_faults": 0,
          "wins": 3
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 108,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 53,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "enabled",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "moonshotai/kimi-k2.7-code",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 51,
          "model": "moonshotai/kimi-k2.7-code",
          "point_rating_method": "sequential_elo",
          "public_id": "E-952fba19b28982d5",
          "rated_matches": 108,
          "raw_elo_rating": 1601.2213719654865,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "enabled",
          "repair_status": "repaired",
          "score": 56.229748233144726,
          "uncertainty": 4.1413142610575715,
          "unilateral_faults": 0,
          "wins": 57
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 176,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 62,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "moonshotai/kimi-k3",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T14:00:00Z",
          "losses": 70,
          "model": "moonshotai/kimi-k3",
          "point_rating_method": "sequential_elo",
          "public_id": "E-895556dde47644ae",
          "rated_matches": 176,
          "raw_elo_rating": 1544.3586605576277,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "first_pass",
          "score": 52.19271965091757,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 106
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 106,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 52,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "enabled",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "nex-agi/nex-n2-pro",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 74,
          "model": "nex-agi/nex-n2-pro",
          "point_rating_method": "sequential_elo",
          "public_id": "E-5f76f577111bee8d",
          "rated_matches": 106,
          "raw_elo_rating": 1281.5487586993647,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "enabled",
          "repair_status": "repaired",
          "score": 29.654555612064655,
          "uncertainty": 4.586824452283178,
          "unilateral_faults": 0,
          "wins": 32
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 114,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 56,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "o3",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 50,
          "model": "o3",
          "point_rating_method": "sequential_elo",
          "public_id": "E-343b92f3dda3dcb5",
          "rated_matches": 114,
          "raw_elo_rating": 1505.8097339730377,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 48.39087874034282,
          "uncertainty": 2.875240412015687,
          "unilateral_faults": 0,
          "wins": 64
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 116,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 56,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "openai/gpt-oss-120b",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 67,
          "model": "openai/gpt-oss-120b",
          "point_rating_method": "sequential_elo",
          "public_id": "E-5ef540286ecbb63d",
          "rated_matches": 116,
          "raw_elo_rating": 1456.517503684909,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "repaired",
          "score": 44.324242271963605,
          "uncertainty": 2.4750163521024238,
          "unilateral_faults": 0,
          "wins": 49
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 176,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 67,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "enabled",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "poolside/laguna-s-2.1",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 138,
          "model": "poolside/laguna-s-2.1",
          "point_rating_method": "sequential_elo",
          "public_id": "E-53ce0020411c86d4",
          "rated_matches": 176,
          "raw_elo_rating": 1135.820841482102,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "enabled",
          "repair_status": "first_pass",
          "score": 18.267761261878103,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 38
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 199,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 71,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "enabled",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "poolside/laguna-s-2.1",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 114,
          "model": "poolside/laguna-s-2.1",
          "point_rating_method": "sequential_elo",
          "public_id": "E-62e15a037ee860c1",
          "rated_matches": 199,
          "raw_elo_rating": 1462.2792203523072,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "enabled",
          "repair_status": "repaired",
          "score": 45.52478884360916,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 85
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 124,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 59,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "enabled",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "qwen/qwen3.7-max",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 63,
          "model": "qwen/qwen3.7-max",
          "point_rating_method": "sequential_elo",
          "public_id": "E-435ec29661cdc285",
          "rated_matches": 124,
          "raw_elo_rating": 1544.3386733865298,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "enabled",
          "repair_status": "repaired",
          "score": 51.71679831534971,
          "uncertainty": 0.9713595499957961,
          "unilateral_faults": 0,
          "wins": 61
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 124,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 58,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "enabled",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "qwen/qwen3.7-plus",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 64,
          "model": "qwen/qwen3.7-plus",
          "point_rating_method": "sequential_elo",
          "public_id": "E-6cc7454f585005c4",
          "rated_matches": 124,
          "raw_elo_rating": 1607.3794802947366,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "enabled",
          "repair_status": "repaired",
          "score": 56.95170350971318,
          "uncertainty": 0.9713595499957961,
          "unilateral_faults": 0,
          "wins": 60
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 20,
          "capped_draws": 0,
          "coverage_status": "under_covered",
          "distinct_rated_opponents": 11,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "qwen/qwen3.8-max",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 8,
          "model": "qwen/qwen3.8-max",
          "point_rating_method": "sequential_elo",
          "public_id": "E-2dec08c905be48b9",
          "rated_matches": 20,
          "raw_elo_rating": 1577.631160970109,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 50.2040113856351,
          "uncertainty": 65.3589451179962,
          "unilateral_faults": 0,
          "wins": 12
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 16,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 8,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "stealth/ox-alpha",
            "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-08-22T00:27:26Z",
          "losses": 10,
          "model": "stealth/ox-alpha",
          "point_rating_method": "sequential_elo",
          "public_id": "E-149dc099de9a50cd",
          "rated_matches": 16,
          "raw_elo_rating": 1449.6235991611914,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "first_pass",
          "score": 38.76653302705747,
          "uncertainty": 77.5178125181665,
          "unilateral_faults": 0,
          "wins": 6
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 16,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 8,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "stealth/ox-alpha",
            "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-08-22T00:27:26Z",
          "losses": 16,
          "model": "stealth/ox-alpha",
          "point_rating_method": "sequential_elo",
          "public_id": "E-6f88d9900795b3a1",
          "rated_matches": 16,
          "raw_elo_rating": 1318.0835583843711,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "first_pass",
          "score": 27.843455158907382,
          "uncertainty": 77.5178125181665,
          "unilateral_faults": 0,
          "wins": 0
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 16,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 8,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "stealth/ox-alpha",
            "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-08-22T00:27:26Z",
          "losses": 8,
          "model": "stealth/ox-alpha",
          "point_rating_method": "sequential_elo",
          "public_id": "E-71c7a6b241c3e968",
          "rated_matches": 16,
          "raw_elo_rating": 1512.5352198384758,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "first_pass",
          "score": 43.99071060379572,
          "uncertainty": 77.5178125181665,
          "unilateral_faults": 0,
          "wins": 8
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 118,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 58,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "stepfun/step-3.7-flash",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 66,
          "model": "stepfun/step-3.7-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-7b9b33921ba865f5",
          "rated_matches": 118,
          "raw_elo_rating": 1491.530653934251,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "repaired",
          "score": 47.2576469157077,
          "uncertainty": 2.084924851410568,
          "unilateral_faults": 0,
          "wins": 52
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 124,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 62,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "thinkingmachines/inkling",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 80,
          "model": "thinkingmachines/inkling",
          "point_rating_method": "sequential_elo",
          "public_id": "E-ae60ed096a69eeff",
          "rated_matches": 124,
          "raw_elo_rating": 1241.8551704733636,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "repaired",
          "score": 26.598584601571144,
          "uncertainty": 0.9713595499957961,
          "unilateral_faults": 0,
          "wins": 44
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 16,
          "capped_draws": 0,
          "coverage_status": "under_covered",
          "distinct_rated_opponents": 8,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "thinkingmachines/inkling-small",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 12,
          "model": "thinkingmachines/inkling-small",
          "point_rating_method": "sequential_elo",
          "public_id": "E-cb36e2fcb99cfafd",
          "rated_matches": 16,
          "raw_elo_rating": 1363.5335221414252,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 31.61761768988316,
          "uncertainty": 77.5178125181665,
          "unilateral_faults": 0,
          "wins": 4
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 116,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 58,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "x-ai/grok-4.5",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T14:00:00Z",
          "losses": 46,
          "model": "x-ai/grok-4.5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-824ec3caceabd338",
          "rated_matches": 116,
          "raw_elo_rating": 1660.642134309636,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 61.274740553352146,
          "uncertainty": 2.4750163521024238,
          "unilateral_faults": 0,
          "wins": 70
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 124,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 57,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "enabled",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "x-ai/grok-build-0.1",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 60,
          "model": "x-ai/grok-build-0.1",
          "point_rating_method": "sequential_elo",
          "public_id": "E-4aac1b6621aeae38",
          "rated_matches": 124,
          "raw_elo_rating": 1685.2701621628198,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "enabled",
          "repair_status": "repaired",
          "score": 63.41974151718129,
          "uncertainty": 0.9713595499957961,
          "unilateral_faults": 0,
          "wins": 64
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 130,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 63,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "enabled",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "xiaomi/mimo-v2.5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 67,
          "model": "xiaomi/mimo-v2.5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-ad48cf51fe7da3cc",
          "rated_matches": 130,
          "raw_elo_rating": 1446.9669001608218,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "enabled",
          "repair_status": "repaired",
          "score": 43.69988545387929,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 63
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 114,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 57,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "xiaomi/mimo-v2.5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T06:10:40Z",
          "losses": 73,
          "model": "xiaomi/mimo-v2.5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-faaa866ee28d6401",
          "rated_matches": 114,
          "raw_elo_rating": 1384.689357216663,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "repaired",
          "score": 38.33304920861673,
          "uncertainty": 2.875240412015687,
          "unilateral_faults": 0,
          "wins": 41
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 110,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 53,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "enabled",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "xiaomi/mimo-v2.5-pro",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 71,
          "model": "xiaomi/mimo-v2.5-pro",
          "point_rating_method": "sequential_elo",
          "public_id": "E-9c228ad72a159b33",
          "rated_matches": 110,
          "raw_elo_rating": 1293.3384425319216,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "enabled",
          "repair_status": "repaired",
          "score": 30.691959004825147,
          "uncertainty": 3.707899787624953,
          "unilateral_faults": 0,
          "wins": 39
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 84,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 42,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "z-ai/glm-5.2",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-11T17:22:09Z",
          "losses": 42,
          "model": "z-ai/glm-5.2",
          "point_rating_method": "sequential_elo",
          "public_id": "E-3916ba303b2ff700",
          "rated_matches": 84,
          "raw_elo_rating": 1563.1378187943271,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "repaired",
          "score": 52.64602705866004,
          "uncertainty": 10.482614454664043,
          "unilateral_faults": 0,
          "wins": 42
        }
      ],
      "GB2-06": [
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 92,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 45,
          "draws": 5,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-fable-5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 22,
          "model": "claude-fable-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-e1ca3ac536f3eb1e",
          "rated_matches": 92,
          "raw_elo_rating": 1815.5838157198623,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 76.8393903737067,
          "uncertainty": 8.09758473652126,
          "unilateral_faults": 0,
          "wins": 65
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 196,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 71,
          "draws": 16,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-opus-4-5",
            "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 82,
          "model": "claude-opus-4-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-1ff6d6f973c7157d",
          "rated_matches": 196,
          "raw_elo_rating": 1500.9782452617544,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 50.754127680852754,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 98
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 0,
          "capped_draws": 0,
          "coverage_status": "pending",
          "distinct_rated_opponents": 0,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "legacy_shared_thinking_budget",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-opus-4-5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "budget",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 0,
          "model": "claude-opus-4-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-8e040f66441f7747",
          "rated_matches": 0,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "budget",
          "reasoning_setting": "legacy_shared_thinking_budget",
          "repair_status": "first_pass",
          "unilateral_faults": 0,
          "wins": 0
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 92,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 46,
          "draws": 1,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-opus-4-8",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 22,
          "model": "claude-opus-4-8",
          "point_rating_method": "sequential_elo",
          "public_id": "E-39e283268f14261d",
          "rated_matches": 92,
          "raw_elo_rating": 1799.7073501929144,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 75.46636108950283,
          "uncertainty": 8.09758473652126,
          "unilateral_faults": 0,
          "wins": 69
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 120,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 59,
          "draws": 4,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-sonnet-5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 54,
          "model": "claude-sonnet-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-01597b81edc004dd",
          "rated_matches": 120,
          "raw_elo_rating": 1443.2412427006718,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 45.08074790155403,
          "uncertainty": 1.7045454545454586,
          "unilateral_faults": 0,
          "wins": 62
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 94,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 44,
          "draws": 3,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-sonnet-5",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 58,
          "model": "claude-sonnet-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-fa6cc450ec345534",
          "rated_matches": 94,
          "raw_elo_rating": 1429.842052186386,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 43.517611811465784,
          "uncertainty": 7.54891760425771,
          "unilateral_faults": 0,
          "wins": 33
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 70,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 35,
          "draws": 1,
          "evaluated_setting_identity": {
            "canonical_provider_route": "unknown_legacy",
            "effective_request_value": "enabled",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "cohere/north-mini-code:free",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 55,
          "model": "cohere/north-mini-code",
          "point_rating_method": "sequential_elo",
          "public_id": "E-78dfcb6ce8b3efaa",
          "rated_matches": 70,
          "raw_elo_rating": 1246.4470947825891,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "enabled",
          "repair_status": "first_pass",
          "score": 27.100975968953843,
          "uncertainty": 15.58908290969266,
          "unilateral_faults": 0,
          "wins": 14
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 80,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 40,
          "draws": 1,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "deepseek/deepseek-v4-flash",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T06:10:40Z",
          "losses": 41,
          "model": "deepseek/deepseek-v4-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-6f20412107151172",
          "rated_matches": 80,
          "raw_elo_rating": 1344.5151990016536,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 35.8438724144747,
          "uncertainty": 11.805555555555554,
          "unilateral_faults": 0,
          "wins": 38
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 80,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 40,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "deepseek/deepseek-v4-flash",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-01T00:15:48Z",
          "losses": 60,
          "model": "deepseek/deepseek-v4-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-d8ca2fcf88af96c7",
          "rated_matches": 80,
          "raw_elo_rating": 1144.0113215973251,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "repaired",
          "score": 18.503886080281386,
          "uncertainty": 11.805555555555554,
          "unilateral_faults": 0,
          "wins": 20
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 132,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 66,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "google/gemini-3.1-flash-lite",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 82,
          "model": "google/gemini-3.1-flash-lite",
          "point_rating_method": "sequential_elo",
          "public_id": "E-a10101fbca309818",
          "rated_matches": 132,
          "raw_elo_rating": 1399.0006395624505,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 41.39995376105174,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 50
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 86,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 43,
          "draws": 11,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "google/gemini-3.5-flash",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 12,
          "model": "google/gemini-3.5-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-35d6e87056063577",
          "rated_matches": 86,
          "raw_elo_rating": 1868.3321704609657,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "repaired",
          "score": 81.27954496028467,
          "uncertainty": 9.855626741889738,
          "unilateral_faults": 0,
          "wins": 63
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 158,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 60,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "google/gemini-3.5-flash-lite",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 136,
          "model": "google/gemini-3.5-flash-lite",
          "point_rating_method": "sequential_elo",
          "public_id": "E-3d6c386b0f48e1c1",
          "rated_matches": 158,
          "raw_elo_rating": 1111.4329647963032,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 16.786700591269984,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 22
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 158,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 60,
          "draws": 4,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "google/gemini-3.5-flash-lite",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 124,
          "model": "google/gemini-3.5-flash-lite",
          "point_rating_method": "sequential_elo",
          "public_id": "E-892a28a528dad9c8",
          "rated_matches": 158,
          "raw_elo_rating": 1178.6148740470483,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 22.596729820598927,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 30
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 154,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 60,
          "draws": 11,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "google/gemini-3.6-flash",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 13,
          "model": "google/gemini-3.6-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-33485e8cce3184c3",
          "rated_matches": 154,
          "raw_elo_rating": 1936.0392948227586,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 88.0651732953837,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 130
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 154,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 61,
          "draws": 10,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "google/gemini-3.6-flash",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 8,
          "model": "google/gemini-3.6-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-bdf020e4fa85b365",
          "rated_matches": 154,
          "raw_elo_rating": 1977.7578215531246,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 91.67307700653463,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 136
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 118,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 58,
          "draws": 1,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "enabled",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "google/gemma-4-31b-it",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 76,
          "model": "google/gemma-4-31b-it",
          "point_rating_method": "sequential_elo",
          "public_id": "E-41987f96551bf9d3",
          "rated_matches": 118,
          "raw_elo_rating": 1333.1575713568993,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "enabled",
          "repair_status": "repaired",
          "score": 35.53416954938754,
          "uncertainty": 2.084924851410568,
          "unilateral_faults": 0,
          "wins": 41
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 104,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 51,
          "draws": 7,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 42,
          "model": "gpt-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-816d262cd933cdb9",
          "rated_matches": 104,
          "raw_elo_rating": 1580.3019624316037,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 56.70292816921177,
          "uncertainty": 5.045003647426665,
          "unilateral_faults": 0,
          "wins": 55
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 82,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 41,
          "draws": 9,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.4",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 5,
          "model": "gpt-5.4",
          "point_rating_method": "sequential_elo",
          "public_id": "E-61f3ed920d3c145d",
          "rated_matches": 82,
          "raw_elo_rating": 1911.8869424079114,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "repaired",
          "score": 84.95793522748247,
          "uncertainty": 11.132129994845172,
          "unilateral_faults": 0,
          "wins": 68
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 92,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 42,
          "draws": 3,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.4",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 8,
          "model": "gpt-5.4",
          "point_rating_method": "sequential_elo",
          "public_id": "E-cbb31028768b544a",
          "rated_matches": 92,
          "raw_elo_rating": 1886.7419988126178,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 82.99329591592327,
          "uncertainty": 8.09758473652126,
          "unilateral_faults": 0,
          "wins": 81
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 108,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 54,
          "draws": 12,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.4-mini",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 43,
          "model": "gpt-5.4-mini",
          "point_rating_method": "sequential_elo",
          "public_id": "E-3ccfe46cbdc271eb",
          "rated_matches": 108,
          "raw_elo_rating": 1559.2793243998406,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 54.94736966606298,
          "uncertainty": 4.1413142610575715,
          "unilateral_faults": 0,
          "wins": 53
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 110,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 55,
          "draws": 3,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.4-nano",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 47,
          "model": "gpt-5.4-nano",
          "point_rating_method": "sequential_elo",
          "public_id": "E-5ccde5c853d97bd9",
          "rated_matches": 110,
          "raw_elo_rating": 1687.0433490489509,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "repaired",
          "score": 66.02665048103961,
          "uncertainty": 3.707899787624953,
          "unilateral_faults": 0,
          "wins": 60
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 104,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 51,
          "draws": 3,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.4-nano",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-09T17:30:50Z",
          "losses": 39,
          "model": "gpt-5.4-nano",
          "point_rating_method": "sequential_elo",
          "public_id": "E-9c5263dcfd4c2ec7",
          "rated_matches": 104,
          "raw_elo_rating": 1581.248219683735,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 56.78476243612473,
          "uncertainty": 5.045003647426665,
          "unilateral_faults": 0,
          "wins": 62
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 122,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 60,
          "draws": 1,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 73,
          "model": "gpt-5.5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-1ea2c2c23d752166",
          "rated_matches": 122,
          "raw_elo_rating": 1468.311575824817,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 47.27455398323267,
          "uncertainty": 1.3334817333716131,
          "unilateral_faults": 0,
          "wins": 48
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 92,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 43,
          "draws": 3,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.6-luna",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 32,
          "model": "gpt-5.6-luna",
          "point_rating_method": "sequential_elo",
          "public_id": "E-6e5d5789ae1ea092",
          "rated_matches": 91,
          "raw_elo_rating": 1617.2068115368675,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 59.663897931635695,
          "uncertainty": 8.378603514268699,
          "unilateral_faults": 1,
          "wins": 56
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 108,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 52,
          "draws": 8,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.6-luna",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-10T10:07:13Z",
          "losses": 34,
          "model": "gpt-5.6-luna",
          "point_rating_method": "sequential_elo",
          "public_id": "E-f4c50b1a9cf2c2e6",
          "rated_matches": 108,
          "raw_elo_rating": 1693.5219286366255,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 66.55694526663,
          "uncertainty": 4.1413142610575715,
          "unilateral_faults": 0,
          "wins": 66
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 92,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 43,
          "draws": 1,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.6-sol",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 53,
          "model": "gpt-5.6-sol",
          "point_rating_method": "sequential_elo",
          "public_id": "E-a106eb47f4726fc8",
          "rated_matches": 92,
          "raw_elo_rating": 1325.565033749482,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 34.46156161117417,
          "uncertainty": 8.09758473652126,
          "unilateral_faults": 0,
          "wins": 38
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 92,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 45,
          "draws": 12,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.6-sol",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-10T10:07:13Z",
          "losses": 16,
          "model": "gpt-5.6-sol",
          "point_rating_method": "sequential_elo",
          "public_id": "E-acdece52463a2698",
          "rated_matches": 92,
          "raw_elo_rating": 1817.2618046108626,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 76.98450629273803,
          "uncertainty": 8.09758473652126,
          "unilateral_faults": 0,
          "wins": 64
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 102,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 51,
          "draws": 12,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.6-terra",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-10T05:30:29Z",
          "losses": 42,
          "model": "gpt-5.6-terra",
          "point_rating_method": "sequential_elo",
          "public_id": "E-a3722334e358f0fe",
          "rated_matches": 102,
          "raw_elo_rating": 1502.2749957494511,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 49.922377861903456,
          "uncertainty": 5.516463908214657,
          "unilateral_faults": 0,
          "wins": 48
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 52,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 26,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "unknown_legacy",
            "effective_request_value": "enabled",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "inclusionai/ling-3.0-flash:free",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 37,
          "model": "inclusionai/ling-3.0-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-6c37c8c2b8e19c4c",
          "rated_matches": 52,
          "raw_elo_rating": 1302.5238444195195,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "enabled",
          "repair_status": "repaired",
          "score": 31.30433139519322,
          "uncertainty": 24.930281974344517,
          "unilateral_faults": 0,
          "wins": 15
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 164,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 61,
          "draws": 11,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "enabled",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "meituan/longcat-2.0",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 115,
          "model": "meituan/longcat-2.0",
          "point_rating_method": "sequential_elo",
          "public_id": "E-0e252768ba2388c4",
          "rated_matches": 164,
          "raw_elo_rating": 1192.2405949843633,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "enabled",
          "repair_status": "first_pass",
          "score": 23.825451789793053,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 38
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 182,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 70,
          "draws": 12,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "enabled",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "meituan/longcat-2.0",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 112,
          "model": "meituan/longcat-2.0",
          "point_rating_method": "sequential_elo",
          "public_id": "E-a9bdeb6a9326ac2d",
          "rated_matches": 182,
          "raw_elo_rating": 1341.1810383570273,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "enabled",
          "repair_status": "repaired",
          "score": 36.841999195974246,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 58
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 120,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 59,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "enabled",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "minimax/minimax-m3",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 79,
          "model": "minimax/minimax-m3",
          "point_rating_method": "sequential_elo",
          "public_id": "E-ef8c1a9fa3580f83",
          "rated_matches": 120,
          "raw_elo_rating": 1342.8613766220567,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "enabled",
          "repair_status": "repaired",
          "score": 36.399691312701414,
          "uncertainty": 1.7045454545454586,
          "unilateral_faults": 0,
          "wins": 41
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 190,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 73,
          "draws": 16,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "moonshotai/kimi-k3",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T14:00:00Z",
          "losses": 74,
          "model": "moonshotai/kimi-k3",
          "point_rating_method": "sequential_elo",
          "public_id": "E-1640f1438f9390d7",
          "rated_matches": 190,
          "raw_elo_rating": 1661.6059928496998,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "repaired",
          "score": 64.6071323338313,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 100
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 106,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 52,
          "draws": 10,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "enabled",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "nex-agi/nex-n2-pro",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 76,
          "model": "nex-agi/nex-n2-pro",
          "point_rating_method": "sequential_elo",
          "public_id": "E-209380b737b62580",
          "rated_matches": 106,
          "raw_elo_rating": 1195.0146527344775,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "enabled",
          "repair_status": "repaired",
          "score": 23.41419124049507,
          "uncertainty": 4.586824452283178,
          "unilateral_faults": 0,
          "wins": 20
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 98,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 47,
          "draws": 8,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "nvidia/nemotron-3-ultra-550b-a55b",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 37,
          "model": "nvidia/nemotron-3-ultra-550b-a55b",
          "point_rating_method": "sequential_elo",
          "public_id": "E-1ea0c8193f35ca72",
          "rated_matches": 98,
          "raw_elo_rating": 1625.0173972189637,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "repaired",
          "score": 60.46921496514469,
          "uncertainty": 6.501890762960602,
          "unilateral_faults": 0,
          "wins": 53
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 106,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 52,
          "draws": 11,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "o3",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 43,
          "model": "o3",
          "point_rating_method": "sequential_elo",
          "public_id": "E-69e964db7b91b1bb",
          "rated_matches": 106,
          "raw_elo_rating": 1597.6476744413671,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 58.234720321902785,
          "uncertainty": 4.586824452283178,
          "unilateral_faults": 0,
          "wins": 52
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 121,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 59,
          "draws": 1,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "openai/gpt-oss-120b",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 78,
          "model": "openai/gpt-oss-120b",
          "point_rating_method": "sequential_elo",
          "public_id": "E-f225b6990e542d31",
          "rated_matches": 121,
          "raw_elo_rating": 1340.0030877685297,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "repaired",
          "score": 36.16541568514887,
          "uncertainty": 1.5178730212592662,
          "unilateral_faults": 0,
          "wins": 42
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 176,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 66,
          "draws": 7,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "enabled",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "poolside/laguna-s-2.1",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 125,
          "model": "poolside/laguna-s-2.1",
          "point_rating_method": "sequential_elo",
          "public_id": "E-b582570ce841ee30",
          "rated_matches": 176,
          "raw_elo_rating": 1156.182973847154,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "enabled",
          "repair_status": "first_pass",
          "score": 20.800006608149722,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 44
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 110,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 52,
          "draws": 12,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "enabled",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "qwen/qwen3.7-max",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 42,
          "model": "qwen/qwen3.7-max",
          "point_rating_method": "sequential_elo",
          "public_id": "E-8283efe6f68a787e",
          "rated_matches": 110,
          "raw_elo_rating": 1579.5531911998273,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "enabled",
          "repair_status": "repaired",
          "score": 56.73068128436687,
          "uncertainty": 3.707899787624953,
          "unilateral_faults": 0,
          "wins": 56
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 100,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 47,
          "draws": 5,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "enabled",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "qwen/qwen3.7-plus",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 31,
          "model": "qwen/qwen3.7-plus",
          "point_rating_method": "sequential_elo",
          "public_id": "E-b6dd11ebe2b80c7b",
          "rated_matches": 100,
          "raw_elo_rating": 1740.616275075024,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "enabled",
          "repair_status": "repaired",
          "score": 70.50103787240695,
          "uncertainty": 6.001859510499461,
          "unilateral_faults": 0,
          "wins": 64
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 20,
          "capped_draws": 0,
          "coverage_status": "under_covered",
          "distinct_rated_opponents": 10,
          "draws": 1,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "qwen/qwen3.8-max",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 6,
          "model": "qwen/qwen3.8-max",
          "point_rating_method": "sequential_elo",
          "public_id": "E-3f0cae67eaa3db85",
          "rated_matches": 20,
          "raw_elo_rating": 1596.932346317202,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 53.968299220992186,
          "uncertainty": 65.3589451179962,
          "unilateral_faults": 0,
          "wins": 13
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 14,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 7,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "stealth/ox-alpha",
            "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-08-22T00:27:26Z",
          "losses": 14,
          "model": "stealth/ox-alpha",
          "point_rating_method": "sequential_elo",
          "public_id": "E-02a3b80bf1513f09",
          "rated_matches": 14,
          "raw_elo_rating": 1327.2247635397769,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "first_pass",
          "score": 29.260379066115735,
          "uncertainty": 85.34944487358055,
          "unilateral_faults": 0,
          "wins": 0
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 14,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 7,
          "draws": 1,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "stealth/ox-alpha",
            "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-08-22T00:27:26Z",
          "losses": 8,
          "model": "stealth/ox-alpha",
          "point_rating_method": "sequential_elo",
          "public_id": "E-3b621d9cad889cf5",
          "rated_matches": 14,
          "raw_elo_rating": 1478.2456762892064,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "repaired",
          "score": 42.32097718099277,
          "uncertainty": 85.34944487358055,
          "unilateral_faults": 0,
          "wins": 5
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 112,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 56,
          "draws": 1,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "stepfun/step-3.7-flash",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 78,
          "model": "stepfun/step-3.7-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-6526762dce98da7c",
          "rated_matches": 112,
          "raw_elo_rating": 1267.48183370103,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "repaired",
          "score": 29.77129697036285,
          "uncertainty": 3.286043419179858,
          "unilateral_faults": 0,
          "wins": 33
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 19,
          "capped_draws": 0,
          "coverage_status": "under_covered",
          "distinct_rated_opponents": 9,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "thinkingmachines/inkling-small",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-08-18T19:25:55Z",
          "losses": 14,
          "model": "thinkingmachines/inkling-small",
          "point_rating_method": "sequential_elo",
          "public_id": "E-76b6aea02c1d6b3d",
          "rated_matches": 19,
          "raw_elo_rating": 1377.382181449011,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "repaired",
          "score": 34.79473339617072,
          "uncertainty": 68.05339887498948,
          "unilateral_faults": 0,
          "wins": 5
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 122,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 59,
          "draws": 8,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "x-ai/grok-4.5",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T14:00:00Z",
          "losses": 62,
          "model": "x-ai/grok-4.5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-3baaff3521870bef",
          "rated_matches": 122,
          "raw_elo_rating": 1443.9671489840152,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 45.169198045990534,
          "uncertainty": 1.3334817333716131,
          "unilateral_faults": 0,
          "wins": 52
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 124,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 57,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "enabled",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "x-ai/grok-build-0.1",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 73,
          "model": "x-ai/grok-build-0.1",
          "point_rating_method": "sequential_elo",
          "public_id": "E-133675db0ee21fd5",
          "rated_matches": 124,
          "raw_elo_rating": 1419.0192370849595,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "enabled",
          "repair_status": "repaired",
          "score": 43.0367051388074,
          "uncertainty": 0.9713595499957961,
          "unilateral_faults": 0,
          "wins": 51
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 124,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 59,
          "draws": 5,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "enabled",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "xiaomi/mimo-v2.5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 77,
          "model": "xiaomi/mimo-v2.5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-7b4c450b6850f156",
          "rated_matches": 124,
          "raw_elo_rating": 1340.4538958273813,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "enabled",
          "repair_status": "repaired",
          "score": 36.242213374439,
          "uncertainty": 0.9713595499957961,
          "unilateral_faults": 0,
          "wins": 42
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 110,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 52,
          "draws": 2,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "enabled",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "xiaomi/mimo-v2.5-pro",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 45,
          "model": "xiaomi/mimo-v2.5-pro",
          "point_rating_method": "sequential_elo",
          "public_id": "E-530f82d65699c577",
          "rated_matches": 110,
          "raw_elo_rating": 1677.2246416402638,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "enabled",
          "repair_status": "repaired",
          "score": 65.17750853680307,
          "uncertainty": 3.707899787624953,
          "unilateral_faults": 0,
          "wins": 63
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 72,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 36,
          "draws": 9,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "z-ai/glm-5.2",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-11T17:22:09Z",
          "losses": 25,
          "model": "z-ai/glm-5.2",
          "point_rating_method": "sequential_elo",
          "public_id": "E-bc40affcf893e495",
          "rated_matches": 72,
          "raw_elo_rating": 1689.1739025328532,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "repaired",
          "score": 65.44552694683463,
          "uncertainty": 14.770573598065289,
          "unilateral_faults": 0,
          "wins": 38
        }
      ],
      "GB2-07": [
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 90,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 45,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-fable-5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 20,
          "model": "claude-fable-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-bc12a8303ec2def7",
          "rated_matches": 90,
          "raw_elo_rating": 1769.0766033480754,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 71.7604520313932,
          "uncertainty": 8.664241836095918,
          "unilateral_faults": 0,
          "wins": 70
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 196,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 74,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-opus-4-5",
            "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 102,
          "model": "claude-opus-4-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-e7848fdc8b4ffd95",
          "rated_matches": 196,
          "raw_elo_rating": 1557.3437342280079,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 53.09835437853516,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 94
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 0,
          "capped_draws": 0,
          "coverage_status": "pending",
          "distinct_rated_opponents": 0,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "legacy_shared_thinking_budget",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-opus-4-5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "budget",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 0,
          "model": "claude-opus-4-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-ed9657bcd9dfeda4",
          "rated_matches": 0,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "budget",
          "reasoning_setting": "legacy_shared_thinking_budget",
          "repair_status": "first_pass",
          "unilateral_faults": 0,
          "wins": 0
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 102,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 51,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-opus-4-8",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 34,
          "model": "claude-opus-4-8",
          "point_rating_method": "sequential_elo",
          "public_id": "E-0bf7b9ed307db853",
          "rated_matches": 102,
          "raw_elo_rating": 1681.4932621274972,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 63.75494931550506,
          "uncertainty": 5.516463908214657,
          "unilateral_faults": 0,
          "wins": 68
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 88,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 44,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-opus-5",
            "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-25T10:50:00Z",
          "losses": 5,
          "model": "claude-opus-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-54bca3ce32fa85ae",
          "rated_matches": 88,
          "raw_elo_rating": 2001.5151284863136,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 93.5912155307729,
          "uncertainty": 9.249894000318006,
          "unilateral_faults": 0,
          "wins": 83
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 108,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 54,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-opus-5",
            "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-25T10:50:00Z",
          "losses": 28,
          "model": "claude-opus-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-de5e72176c4f0dc9",
          "rated_matches": 108,
          "raw_elo_rating": 1841.6595764381452,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 78.93177963820368,
          "uncertainty": 4.1413142610575715,
          "unilateral_faults": 0,
          "wins": 80
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 124,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 60,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-sonnet-5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 52,
          "model": "claude-sonnet-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-9e40526fba9fa8b9",
          "rated_matches": 124,
          "raw_elo_rating": 1528.418380946387,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 49.69122123778862,
          "uncertainty": 0.9713595499957961,
          "unilateral_faults": 0,
          "wins": 72
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 90,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 42,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-sonnet-5",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 39,
          "model": "claude-sonnet-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-a0f9e38d7d75c542",
          "rated_matches": 90,
          "raw_elo_rating": 1538.9093254268835,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 50.09934354410103,
          "uncertainty": 8.664241836095918,
          "unilateral_faults": 0,
          "wins": 51
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 76,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 38,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "unknown_legacy",
            "effective_request_value": "enabled",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "cohere/north-mini-code:free",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 47,
          "model": "cohere/north-mini-code",
          "point_rating_method": "sequential_elo",
          "public_id": "E-1c961fde1b53f0eb",
          "rated_matches": 76,
          "raw_elo_rating": 1378.8995385942992,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "enabled",
          "repair_status": "repaired",
          "score": 34.697007101399166,
          "uncertainty": 13.230288229818967,
          "unilateral_faults": 0,
          "wins": 29
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 76,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 38,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "deepseek/deepseek-v4-flash",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-01T00:15:48Z",
          "losses": 49,
          "model": "deepseek/deepseek-v4-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-8f2f6c973751f183",
          "rated_matches": 76,
          "raw_elo_rating": 1320.1500414871316,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 29.168075092011048,
          "uncertainty": 13.230288229818967,
          "unilateral_faults": 0,
          "wins": 27
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 76,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 38,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "deepseek/deepseek-v4-flash",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T06:10:40Z",
          "losses": 40,
          "model": "deepseek/deepseek-v4-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-edc2d085c4253ed3",
          "rated_matches": 76,
          "raw_elo_rating": 1490.5838262704146,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 45.20764742146505,
          "uncertainty": 13.230288229818967,
          "unilateral_faults": 0,
          "wins": 36
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 94,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 45,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "google/gemini-3.1-flash-lite",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 82,
          "model": "google/gemini-3.1-flash-lite",
          "point_rating_method": "sequential_elo",
          "public_id": "E-1b3c52da51dfbdd4",
          "rated_matches": 94,
          "raw_elo_rating": 1011.5193889215823,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "repaired",
          "score": 0.5504962648416883,
          "uncertainty": 7.54891760425771,
          "unilateral_faults": 0,
          "wins": 12
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 108,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 53,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "google/gemini-3.5-flash",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 53,
          "model": "google/gemini-3.5-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-5447c508e2b0ab6c",
          "rated_matches": 108,
          "raw_elo_rating": 1543.7114866663292,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "repaired",
          "score": 50.89179952279148,
          "uncertainty": 4.1413142610575715,
          "unilateral_faults": 0,
          "wins": 55
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 156,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 62,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "google/gemini-3.5-flash-lite",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 117,
          "model": "google/gemini-3.5-flash-lite",
          "point_rating_method": "sequential_elo",
          "public_id": "E-f74134262b66367b",
          "rated_matches": 156,
          "raw_elo_rating": 1158.879352478688,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 15.276461919221447,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 39
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 156,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 64,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "google/gemini-3.6-flash",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 65,
          "model": "google/gemini-3.6-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-1f7519ff2c4a840c",
          "rated_matches": 156,
          "raw_elo_rating": 1671.4301764240602,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 63.512766849295424,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 91
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 130,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 65,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "google/gemini-3.6-flash",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 55,
          "model": "google/gemini-3.6-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-65c6c8e09fe2c210",
          "rated_matches": 130,
          "raw_elo_rating": 1459.9241308797457,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 43.32321813916118,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 75
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 110,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 52,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "enabled",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "google/gemma-4-31b-it",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 57,
          "model": "google/gemma-4-31b-it",
          "point_rating_method": "sequential_elo",
          "public_id": "E-f417d302c870dfa6",
          "rated_matches": 110,
          "raw_elo_rating": 1408.849027987095,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "enabled",
          "repair_status": "repaired",
          "score": 38.232485895385615,
          "uncertainty": 3.707899787624953,
          "unilateral_faults": 0,
          "wins": 53
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 100,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 50,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 40,
          "model": "gpt-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-4d8b4cfcff519db6",
          "rated_matches": 100,
          "raw_elo_rating": 1636.8698724185067,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "repaired",
          "score": 59.51888474627783,
          "uncertainty": 6.001859510499461,
          "unilateral_faults": 0,
          "wins": 60
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 98,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 43,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.4",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 60,
          "model": "gpt-5.4",
          "point_rating_method": "sequential_elo",
          "public_id": "E-1d11cba509a3ee65",
          "rated_matches": 98,
          "raw_elo_rating": 1388.7768974869502,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 36.13313730855662,
          "uncertainty": 6.501890762960602,
          "unilateral_faults": 0,
          "wins": 38
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 102,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 50,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.4",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 35,
          "model": "gpt-5.4",
          "point_rating_method": "sequential_elo",
          "public_id": "E-22466ae84d7027e5",
          "rated_matches": 102,
          "raw_elo_rating": 1644.7476027576552,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 60.29680478151199,
          "uncertainty": 5.516463908214657,
          "unilateral_faults": 0,
          "wins": 67
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 108,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 53,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.4-mini",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 48,
          "model": "gpt-5.4-mini",
          "point_rating_method": "sequential_elo",
          "public_id": "E-f4d7ac8a0f5d2974",
          "rated_matches": 108,
          "raw_elo_rating": 1562.733366371016,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 52.68195407315516,
          "uncertainty": 4.1413142610575715,
          "unilateral_faults": 0,
          "wins": 60
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 94,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 46,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.4-nano",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 78,
          "model": "gpt-5.4-nano",
          "point_rating_method": "sequential_elo",
          "public_id": "E-bea6d7d9558897f9",
          "rated_matches": 94,
          "raw_elo_rating": 1161.1653460942716,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 14.633720180415708,
          "uncertainty": 7.54891760425771,
          "unilateral_faults": 0,
          "wins": 16
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 100,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 50,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.4-nano",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-09T17:30:50Z",
          "losses": 35,
          "model": "gpt-5.4-nano",
          "point_rating_method": "sequential_elo",
          "public_id": "E-ce04fd14b6f43868",
          "rated_matches": 100,
          "raw_elo_rating": 1645.247290829246,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "repaired",
          "score": 60.30728599374183,
          "uncertainty": 6.001859510499461,
          "unilateral_faults": 0,
          "wins": 65
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 94,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 46,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 32,
          "model": "gpt-5.5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-640b3078b8bce40e",
          "rated_matches": 94,
          "raw_elo_rating": 1740.3549601868879,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 69.14142074882011,
          "uncertainty": 7.54891760425771,
          "unilateral_faults": 0,
          "wins": 62
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 114,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 54,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.6-luna",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-10T05:30:29Z",
          "losses": 64,
          "model": "gpt-5.6-luna",
          "point_rating_method": "sequential_elo",
          "public_id": "E-45c76cf9faaba10a",
          "rated_matches": 114,
          "raw_elo_rating": 1488.6145781538792,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 45.80193413103889,
          "uncertainty": 2.875240412015687,
          "unilateral_faults": 0,
          "wins": 50
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 90,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 43,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.6-luna",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 61,
          "model": "gpt-5.6-luna",
          "point_rating_method": "sequential_elo",
          "public_id": "E-af6cc32d5ba04b84",
          "rated_matches": 90,
          "raw_elo_rating": 1333.7149739611784,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 30.788444322361737,
          "uncertainty": 8.664241836095918,
          "unilateral_faults": 0,
          "wins": 29
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 92,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 43,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.6-sol",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 11,
          "model": "gpt-5.6-sol",
          "point_rating_method": "sequential_elo",
          "public_id": "E-6e22708296e06d4c",
          "rated_matches": 92,
          "raw_elo_rating": 1850.56158757978,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 79.47168985931388,
          "uncertainty": 8.09758473652126,
          "unilateral_faults": 0,
          "wins": 81
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 98,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 49,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.6-sol",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-10T05:30:29Z",
          "losses": 38,
          "model": "gpt-5.6-sol",
          "point_rating_method": "sequential_elo",
          "public_id": "E-cc78d54d18d4c3f1",
          "rated_matches": 98,
          "raw_elo_rating": 1648.549683693386,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 60.5804286650213,
          "uncertainty": 6.501890762960602,
          "unilateral_faults": 0,
          "wins": 60
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 114,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 56,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.6-terra",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-10T05:30:29Z",
          "losses": 59,
          "model": "gpt-5.6-terra",
          "point_rating_method": "sequential_elo",
          "public_id": "E-aca193dd2a8774fb",
          "rated_matches": 114,
          "raw_elo_rating": 1379.3006758761821,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "repaired",
          "score": 35.51437146013137,
          "uncertainty": 2.875240412015687,
          "unilateral_faults": 0,
          "wins": 55
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 52,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 26,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "unknown_legacy",
            "effective_request_value": "enabled",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "inclusionai/ling-3.0-flash:free",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 29,
          "model": "inclusionai/ling-3.0-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-57b2b1d3b488c246",
          "rated_matches": 52,
          "raw_elo_rating": 1479.394616306791,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "enabled",
          "repair_status": "repaired",
          "score": 43.27375585368886,
          "uncertainty": 24.930281974344517,
          "unilateral_faults": 0,
          "wins": 23
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 52,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 26,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "unknown_legacy",
            "effective_request_value": "enabled",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "inclusionai/ling-3.0-flash:free",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 33,
          "model": "inclusionai/ling-3.0-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-5e20a850f6c14680",
          "rated_matches": 52,
          "raw_elo_rating": 1411.6900153869835,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "enabled",
          "repair_status": "repaired",
          "score": 36.90205645810878,
          "uncertainty": 24.930281974344517,
          "unilateral_faults": 0,
          "wins": 19
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 166,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 66,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "enabled",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "meituan/longcat-2.0",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 62,
          "model": "meituan/longcat-2.0",
          "point_rating_method": "sequential_elo",
          "public_id": "E-28ec7bff448d69bb",
          "rated_matches": 166,
          "raw_elo_rating": 1651.2939940426838,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "enabled",
          "repair_status": "first_pass",
          "score": 61.709083324168645,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 104
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 156,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 60,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "enabled",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "meituan/longcat-2.0",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 129,
          "model": "meituan/longcat-2.0",
          "point_rating_method": "sequential_elo",
          "public_id": "E-fe21773d3155f05f",
          "rated_matches": 156,
          "raw_elo_rating": 1094.481412085471,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "enabled",
          "repair_status": "first_pass",
          "score": 9.215953293432932,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 27
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 92,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 43,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "meta/muse-spark-1.2",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-08-13T16:58:34Z",
          "losses": 22,
          "model": "meta/muse-spark-1.2",
          "point_rating_method": "sequential_elo",
          "public_id": "E-ab39e2e398a78370",
          "rated_matches": 92,
          "raw_elo_rating": 1713.3713882243446,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 66.56068088153548,
          "uncertainty": 8.09758473652126,
          "unilateral_faults": 0,
          "wins": 70
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 120,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 56,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "enabled",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "minimax/minimax-m3",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 58,
          "model": "minimax/minimax-m3",
          "point_rating_method": "sequential_elo",
          "public_id": "E-4547f4cedca403f9",
          "rated_matches": 120,
          "raw_elo_rating": 1487.907737533893,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "enabled",
          "repair_status": "repaired",
          "score": 45.82355270808264,
          "uncertainty": 1.7045454545454586,
          "unilateral_faults": 0,
          "wins": 62
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 116,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 55,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "enabled",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "moonshotai/kimi-k2.7-code",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 53,
          "model": "moonshotai/kimi-k2.7-code",
          "point_rating_method": "sequential_elo",
          "public_id": "E-d35e87ebfc251f60",
          "rated_matches": 116,
          "raw_elo_rating": 1503.7235320013426,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "enabled",
          "repair_status": "repaired",
          "score": 47.25397426838036,
          "uncertainty": 2.4750163521024238,
          "unilateral_faults": 0,
          "wins": 63
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 160,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 62,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "moonshotai/kimi-k3",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T14:00:00Z",
          "losses": 112,
          "model": "moonshotai/kimi-k3",
          "point_rating_method": "sequential_elo",
          "public_id": "E-55ef4536a723bcf7",
          "rated_matches": 160,
          "raw_elo_rating": 1302.1666353464232,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "first_pass",
          "score": 28.7988247426727,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 48
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 112,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 54,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "enabled",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "nex-agi/nex-n2-pro",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 59,
          "model": "nex-agi/nex-n2-pro",
          "point_rating_method": "sequential_elo",
          "public_id": "E-d1f432cda667f27f",
          "rated_matches": 112,
          "raw_elo_rating": 1454.1203052409805,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "enabled",
          "repair_status": "repaired",
          "score": 42.524739590732,
          "uncertainty": 3.286043419179858,
          "unilateral_faults": 0,
          "wins": 53
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 92,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 44,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "nvidia/nemotron-3-ultra-550b-a55b",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 72,
          "model": "nvidia/nemotron-3-ultra-550b-a55b",
          "point_rating_method": "sequential_elo",
          "public_id": "E-459f395cc0af6d2e",
          "rated_matches": 92,
          "raw_elo_rating": 1120.4180547333053,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "repaired",
          "score": 10.757672736091521,
          "uncertainty": 8.09758473652126,
          "unilateral_faults": 0,
          "wins": 20
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 106,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 53,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "o3",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 42,
          "model": "o3",
          "point_rating_method": "sequential_elo",
          "public_id": "E-f1e3e54a3d40556f",
          "rated_matches": 106,
          "raw_elo_rating": 1636.9247706055485,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 59.630586714276724,
          "uncertainty": 4.586824452283178,
          "unilateral_faults": 0,
          "wins": 64
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 86,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 43,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "enabled",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "qwen/qwen3.7-max",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 21,
          "model": "qwen/qwen3.7-max",
          "point_rating_method": "sequential_elo",
          "public_id": "E-59c7745eb1e91d63",
          "rated_matches": 86,
          "raw_elo_rating": 1780.9950468049765,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "enabled",
          "repair_status": "repaired",
          "score": 72.79240290081826,
          "uncertainty": 9.855626741889738,
          "unilateral_faults": 0,
          "wins": 65
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 114,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 55,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "enabled",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "qwen/qwen3.7-plus",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 57,
          "model": "qwen/qwen3.7-plus",
          "point_rating_method": "sequential_elo",
          "public_id": "E-9d091700cb41ece2",
          "rated_matches": 114,
          "raw_elo_rating": 1450.7149866418183,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "enabled",
          "repair_status": "repaired",
          "score": 42.23519271244378,
          "uncertainty": 2.875240412015687,
          "unilateral_faults": 0,
          "wins": 57
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 18,
          "capped_draws": 0,
          "coverage_status": "under_covered",
          "distinct_rated_opponents": 10,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "qwen/qwen3.8-max",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 10,
          "model": "qwen/qwen3.8-max",
          "point_rating_method": "sequential_elo",
          "public_id": "E-1f83b2062e021657",
          "rated_matches": 18,
          "raw_elo_rating": 1452.2408415859013,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 37.2529709637503,
          "uncertainty": 70.95786693528086,
          "unilateral_faults": 0,
          "wins": 8
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 16,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 8,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "stealth/ox-alpha",
            "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-08-22T00:27:26Z",
          "losses": 16,
          "model": "stealth/ox-alpha",
          "point_rating_method": "sequential_elo",
          "public_id": "E-90df0bc1145d0335",
          "rated_matches": 16,
          "raw_elo_rating": 1311.2344400533552,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "first_pass",
          "score": 23.488931418402004,
          "uncertainty": 77.5178125181665,
          "unilateral_faults": 0,
          "wins": 0
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 16,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 8,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "stealth/ox-alpha",
            "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-08-22T00:27:26Z",
          "losses": 12,
          "model": "stealth/ox-alpha",
          "point_rating_method": "sequential_elo",
          "public_id": "E-9cc97e533afb41b3",
          "rated_matches": 16,
          "raw_elo_rating": 1410.7754751963084,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "first_pass",
          "score": 32.85676676251696,
          "uncertainty": 77.5178125181665,
          "unilateral_faults": 0,
          "wins": 4
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 16,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 8,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "stealth/ox-alpha",
            "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-08-22T00:27:26Z",
          "losses": 0,
          "model": "stealth/ox-alpha",
          "point_rating_method": "sequential_elo",
          "public_id": "E-ae808d1219edf709",
          "rated_matches": 16,
          "raw_elo_rating": 1678.926051188307,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "first_pass",
          "score": 58.09249431663672,
          "uncertainty": 77.5178125181665,
          "unilateral_faults": 0,
          "wins": 16
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 156,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 61,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "thinkingmachines/inkling",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 139,
          "model": "thinkingmachines/inkling",
          "point_rating_method": "sequential_elo",
          "public_id": "E-b9ceec0ad4a1b9a4",
          "rated_matches": 156,
          "raw_elo_rating": 1082.0671538643896,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 8.04764389452622,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 17
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 19,
          "capped_draws": 0,
          "coverage_status": "under_covered",
          "distinct_rated_opponents": 9,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "thinkingmachines/inkling-small",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 8,
          "model": "thinkingmachines/inkling-small",
          "point_rating_method": "sequential_elo",
          "public_id": "E-b205e1d25c695262",
          "rated_matches": 19,
          "raw_elo_rating": 1542.484591986778,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 45.96450843356181,
          "uncertainty": 68.05339887498948,
          "unilateral_faults": 0,
          "wins": 11
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 112,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 56,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "x-ai/grok-4.5",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T14:00:00Z",
          "losses": 47,
          "model": "x-ai/grok-4.5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-e58f3df122cf1d29",
          "rated_matches": 112,
          "raw_elo_rating": 1656.3784608491428,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "repaired",
          "score": 61.55931257885285,
          "uncertainty": 3.286043419179858,
          "unilateral_faults": 0,
          "wins": 65
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 106,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 50,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "enabled",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "x-ai/grok-build-0.1",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 73,
          "model": "x-ai/grok-build-0.1",
          "point_rating_method": "sequential_elo",
          "public_id": "E-37ae0129627ee16f",
          "rated_matches": 106,
          "raw_elo_rating": 1249.6710367295523,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "enabled",
          "repair_status": "repaired",
          "score": 23.186026838702013,
          "uncertainty": 4.586824452283178,
          "unilateral_faults": 0,
          "wins": 33
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 96,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 44,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "xiaomi/mimo-v2.5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-01T00:15:48Z",
          "losses": 45,
          "model": "xiaomi/mimo-v2.5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-345a5b25cbac7f3b",
          "rated_matches": 96,
          "raw_elo_rating": 1536.730322602996,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 50.01827167679295,
          "uncertainty": 7.017308256680951,
          "unilateral_faults": 0,
          "wins": 51
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 104,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 50,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "enabled",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "xiaomi/mimo-v2.5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 58,
          "model": "xiaomi/mimo-v2.5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-fa1a93f7e4d57000",
          "rated_matches": 104,
          "raw_elo_rating": 1324.660786450052,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "enabled",
          "repair_status": "repaired",
          "score": 30.208838175428983,
          "uncertainty": 5.045003647426665,
          "unilateral_faults": 0,
          "wins": 46
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 120,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 59,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "enabled",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "xiaomi/mimo-v2.5-pro",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 62,
          "model": "xiaomi/mimo-v2.5-pro",
          "point_rating_method": "sequential_elo",
          "public_id": "E-3b160130ae038271",
          "rated_matches": 120,
          "raw_elo_rating": 1467.492796093447,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "enabled",
          "repair_status": "repaired",
          "score": 43.90229671853825,
          "uncertainty": 1.7045454545454586,
          "unilateral_faults": 0,
          "wins": 58
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 82,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 41,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "z-ai/glm-5.2",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-11T17:22:09Z",
          "losses": 34,
          "model": "z-ai/glm-5.2",
          "point_rating_method": "sequential_elo",
          "public_id": "E-ecd98326faa92bf4",
          "rated_matches": 82,
          "raw_elo_rating": 1539.4625749629602,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "repaired",
          "score": 49.96560708699275,
          "uncertainty": 11.132129994845172,
          "unilateral_faults": 0,
          "wins": 48
        }
      ],
      "GB2-08": [
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 92,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 45,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-fable-5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 12,
          "model": "claude-fable-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-9ccf296d44d35675",
          "rated_matches": 92,
          "raw_elo_rating": 1817.575241405041,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 74.2473959519865,
          "uncertainty": 8.09758473652126,
          "unilateral_faults": 0,
          "wins": 80
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 0,
          "capped_draws": 0,
          "coverage_status": "pending",
          "distinct_rated_opponents": 0,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "legacy_shared_thinking_budget",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-opus-4-5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "budget",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 0,
          "model": "claude-opus-4-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-355427eb0d526f34",
          "rated_matches": 0,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "budget",
          "reasoning_setting": "legacy_shared_thinking_budget",
          "repair_status": "first_pass",
          "unilateral_faults": 0,
          "wins": 0
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 176,
          "capped_draws": 2,
          "coverage_status": "rated",
          "distinct_rated_opponents": 73,
          "draws": 2,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-opus-4-5",
            "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 28,
          "model": "claude-opus-4-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-72233463ddce5549",
          "rated_matches": 176,
          "raw_elo_rating": 1884.3566176372763,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 82.15300774815739,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 146
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 110,
          "capped_draws": 84,
          "coverage_status": "rated",
          "distinct_rated_opponents": 54,
          "draws": 84,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-opus-4-8",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 21,
          "model": "claude-opus-4-8",
          "point_rating_method": "sequential_elo",
          "public_id": "E-c2dade0b97891d8a",
          "rated_matches": 110,
          "raw_elo_rating": 1395.7974788159802,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 31.959425881493154,
          "uncertainty": 3.707899787624953,
          "unilateral_faults": 0,
          "wins": 5
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 102,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 51,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-opus-5",
            "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-25T10:50:00Z",
          "losses": 20,
          "model": "claude-opus-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-35a5bf9b35d5e1e8",
          "rated_matches": 102,
          "raw_elo_rating": 1862.4936313700762,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 78.99754956052814,
          "uncertainty": 5.516463908214657,
          "unilateral_faults": 0,
          "wins": 82
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 104,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 52,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-opus-5",
            "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-25T10:50:00Z",
          "losses": 8,
          "model": "claude-opus-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-e73b6fb78880341d",
          "rated_matches": 104,
          "raw_elo_rating": 1990.1371275012355,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 91.94082927402685,
          "uncertainty": 5.045003647426665,
          "unilateral_faults": 0,
          "wins": 96
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 88,
          "capped_draws": 52,
          "coverage_status": "rated",
          "distinct_rated_opponents": 42,
          "draws": 52,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-sonnet-5",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 29,
          "model": "claude-sonnet-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-01c56a1fc7407264",
          "rated_matches": 88,
          "raw_elo_rating": 1384.3413005388531,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 30.352921291303954,
          "uncertainty": 9.249894000318006,
          "unilateral_faults": 0,
          "wins": 7
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 112,
          "capped_draws": 85,
          "coverage_status": "rated",
          "distinct_rated_opponents": 56,
          "draws": 85,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-sonnet-5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 20,
          "model": "claude-sonnet-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-130fb40b1c7a4d39",
          "rated_matches": 112,
          "raw_elo_rating": 1407.0267536166316,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 33.12886059328138,
          "uncertainty": 3.286043419179858,
          "unilateral_faults": 0,
          "wins": 7
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 68,
          "capped_draws": 50,
          "coverage_status": "rated",
          "distinct_rated_opponents": 34,
          "draws": 50,
          "evaluated_setting_identity": {
            "canonical_provider_route": "unknown_legacy",
            "effective_request_value": "enabled",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "cohere/north-mini-code:free",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 18,
          "model": "cohere/north-mini-code",
          "point_rating_method": "sequential_elo",
          "public_id": "E-efd7b75d5cd3b538",
          "rated_matches": 68,
          "raw_elo_rating": 1381.6595847116837,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "enabled",
          "repair_status": "first_pass",
          "score": 29.500001613253012,
          "uncertainty": 16.4429265428846,
          "unilateral_faults": 0,
          "wins": 0
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 80,
          "capped_draws": 71,
          "coverage_status": "rated",
          "distinct_rated_opponents": 40,
          "draws": 71,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "deepseek/deepseek-v4-flash",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T06:10:40Z",
          "losses": 7,
          "model": "deepseek/deepseek-v4-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-43aba68125a9abc5",
          "rated_matches": 80,
          "raw_elo_rating": 1423.616337969348,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 34.11703924691805,
          "uncertainty": 11.805555555555554,
          "unilateral_faults": 0,
          "wins": 2
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 84,
          "capped_draws": 73,
          "coverage_status": "rated",
          "distinct_rated_opponents": 42,
          "draws": 73,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "deepseek/deepseek-v4-flash",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-01T00:15:48Z",
          "losses": 9,
          "model": "deepseek/deepseek-v4-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-d28ef17ff6995c62",
          "rated_matches": 84,
          "raw_elo_rating": 1364.473428735264,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "repaired",
          "score": 28.244513402803264,
          "uncertainty": 10.482614454664043,
          "unilateral_faults": 0,
          "wins": 2
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 132,
          "capped_draws": 40,
          "coverage_status": "rated",
          "distinct_rated_opponents": 66,
          "draws": 40,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "google/gemini-3.1-flash-lite",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 51,
          "model": "google/gemini-3.1-flash-lite",
          "point_rating_method": "sequential_elo",
          "public_id": "E-cc6fb78c96472032",
          "rated_matches": 132,
          "raw_elo_rating": 1434.8578660442124,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 36.2403624207267,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 41
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 90,
          "capped_draws": 68,
          "coverage_status": "rated",
          "distinct_rated_opponents": 45,
          "draws": 68,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "google/gemini-3.5-flash",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 22,
          "model": "google/gemini-3.5-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-bd0bbefbbd252fc5",
          "rated_matches": 90,
          "raw_elo_rating": 1332.5013086471351,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "repaired",
          "score": 25.159108940712393,
          "uncertainty": 8.664241836095918,
          "unilateral_faults": 0,
          "wins": 0
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 164,
          "capped_draws": 113,
          "coverage_status": "rated",
          "distinct_rated_opponents": 62,
          "draws": 113,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "google/gemini-3.5-flash-lite",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 44,
          "model": "google/gemini-3.5-flash-lite",
          "point_rating_method": "sequential_elo",
          "public_id": "E-2f2aa5b1beafd6e6",
          "rated_matches": 164,
          "raw_elo_rating": 1329.6384448839742,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 25.960711751224267,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 7
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 156,
          "capped_draws": 104,
          "coverage_status": "rated",
          "distinct_rated_opponents": 58,
          "draws": 104,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "google/gemini-3.5-flash-lite",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 46,
          "model": "google/gemini-3.5-flash-lite",
          "point_rating_method": "sequential_elo",
          "public_id": "E-9b50de854a87d3c6",
          "rated_matches": 156,
          "raw_elo_rating": 1338.4133394571838,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 26.768664341028472,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 6
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 148,
          "capped_draws": 22,
          "coverage_status": "rated",
          "distinct_rated_opponents": 62,
          "draws": 22,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "google/gemini-3.6-flash",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 35,
          "model": "google/gemini-3.6-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-ab7ee826f8050f04",
          "rated_matches": 148,
          "raw_elo_rating": 1758.2226139935103,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 69.12714958998048,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 91
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 90,
          "capped_draws": 56,
          "coverage_status": "rated",
          "distinct_rated_opponents": 43,
          "draws": 56,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 26,
          "model": "gpt-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-04ae9f2b42e0e036",
          "rated_matches": 90,
          "raw_elo_rating": 1347.8497544240654,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 26.71088363179663,
          "uncertainty": 8.664241836095918,
          "unilateral_faults": 0,
          "wins": 8
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 103,
          "capped_draws": 53,
          "coverage_status": "rated",
          "distinct_rated_opponents": 47,
          "draws": 53,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.4",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 23,
          "model": "gpt-5.4",
          "point_rating_method": "sequential_elo",
          "public_id": "E-6b601c15cf117b79",
          "rated_matches": 103,
          "raw_elo_rating": 1478.262264289942,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 40.16979011364343,
          "uncertainty": 5.279033784546012,
          "unilateral_faults": 0,
          "wins": 27
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 102,
          "capped_draws": 39,
          "coverage_status": "rated",
          "distinct_rated_opponents": 50,
          "draws": 39,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.4",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 31,
          "model": "gpt-5.4",
          "point_rating_method": "sequential_elo",
          "public_id": "E-b13a2be40d59c1ea",
          "rated_matches": 102,
          "raw_elo_rating": 1477.125133604714,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 40.03561880449786,
          "uncertainty": 5.516463908214657,
          "unilateral_faults": 0,
          "wins": 32
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 114,
          "capped_draws": 41,
          "coverage_status": "rated",
          "distinct_rated_opponents": 54,
          "draws": 41,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.4-mini",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 38,
          "model": "gpt-5.4-mini",
          "point_rating_method": "sequential_elo",
          "public_id": "E-b5171a15f0048555",
          "rated_matches": 114,
          "raw_elo_rating": 1435.5819424274005,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 36.04910404429471,
          "uncertainty": 2.875240412015687,
          "unilateral_faults": 0,
          "wins": 35
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 94,
          "capped_draws": 52,
          "coverage_status": "rated",
          "distinct_rated_opponents": 46,
          "draws": 52,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.4-nano",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 37,
          "model": "gpt-5.4-nano",
          "point_rating_method": "sequential_elo",
          "public_id": "E-26fa12e871bd8f3a",
          "rated_matches": 94,
          "raw_elo_rating": 1333.8577876317347,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "repaired",
          "score": 25.3864632500842,
          "uncertainty": 7.54891760425771,
          "unilateral_faults": 0,
          "wins": 5
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 94,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 46,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.4-nano",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-09T17:30:50Z",
          "losses": 22,
          "model": "gpt-5.4-nano",
          "point_rating_method": "sequential_elo",
          "public_id": "E-e361d8cbba2abd67",
          "rated_matches": 94,
          "raw_elo_rating": 1848.361904518589,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "repaired",
          "score": 77.40439904940192,
          "uncertainty": 7.54891760425771,
          "unilateral_faults": 0,
          "wins": 72
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 112,
          "capped_draws": 50,
          "coverage_status": "rated",
          "distinct_rated_opponents": 55,
          "draws": 50,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 24,
          "model": "gpt-5.5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-0d83a3c5c5e66085",
          "rated_matches": 112,
          "raw_elo_rating": 1602.1188603960716,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 52.85326775023768,
          "uncertainty": 3.286043419179858,
          "unilateral_faults": 0,
          "wins": 38
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 90,
          "capped_draws": 55,
          "coverage_status": "rated",
          "distinct_rated_opponents": 42,
          "draws": 55,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.6-luna",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 32,
          "model": "gpt-5.6-luna",
          "point_rating_method": "sequential_elo",
          "public_id": "E-283f17e4d25ffd65",
          "rated_matches": 90,
          "raw_elo_rating": 1323.5572279214625,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 24.254835093911925,
          "uncertainty": 8.664241836095918,
          "unilateral_faults": 0,
          "wins": 3
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 114,
          "capped_draws": 89,
          "coverage_status": "rated",
          "distinct_rated_opponents": 56,
          "draws": 89,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.6-luna",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-10T05:30:29Z",
          "losses": 18,
          "model": "gpt-5.6-luna",
          "point_rating_method": "sequential_elo",
          "public_id": "E-e6198d88365e0492",
          "rated_matches": 114,
          "raw_elo_rating": 1411.463867477643,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 33.610693090596705,
          "uncertainty": 2.875240412015687,
          "unilateral_faults": 0,
          "wins": 7
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 88,
          "capped_draws": 5,
          "coverage_status": "rated",
          "distinct_rated_opponents": 44,
          "draws": 5,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.6-sol",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-10T05:30:29Z",
          "losses": 19,
          "model": "gpt-5.6-sol",
          "point_rating_method": "sequential_elo",
          "public_id": "E-0385f0602a8e29e2",
          "rated_matches": 88,
          "raw_elo_rating": 1776.669530520418,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 70.01850220623565,
          "uncertainty": 9.249894000318006,
          "unilateral_faults": 0,
          "wins": 64
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 90,
          "capped_draws": 20,
          "coverage_status": "rated",
          "distinct_rated_opponents": 42,
          "draws": 20,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.6-sol",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 17,
          "model": "gpt-5.6-sol",
          "point_rating_method": "sequential_elo",
          "public_id": "E-55079a10c13f4211",
          "rated_matches": 90,
          "raw_elo_rating": 1652.9687749937566,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 57.5593474287059,
          "uncertainty": 8.664241836095918,
          "unilateral_faults": 0,
          "wins": 53
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 108,
          "capped_draws": 53,
          "coverage_status": "rated",
          "distinct_rated_opponents": 53,
          "draws": 53,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.6-terra",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-10T05:30:29Z",
          "losses": 34,
          "model": "gpt-5.6-terra",
          "point_rating_method": "sequential_elo",
          "public_id": "E-d004e78844cdd202",
          "rated_matches": 108,
          "raw_elo_rating": 1480.0543554717117,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 40.442997530903185,
          "uncertainty": 4.1413142610575715,
          "unilateral_faults": 0,
          "wins": 21
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 168,
          "capped_draws": 47,
          "coverage_status": "rated",
          "distinct_rated_opponents": 61,
          "draws": 47,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "enabled",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "meituan/longcat-2.0",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 120,
          "model": "meituan/longcat-2.0",
          "point_rating_method": "sequential_elo",
          "public_id": "E-d724da56cbc06da7",
          "rated_matches": 168,
          "raw_elo_rating": 1121.9065676781295,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "enabled",
          "repair_status": "first_pass",
          "score": 4.995866874780885,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 1
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 143,
          "capped_draws": 50,
          "coverage_status": "rated",
          "distinct_rated_opponents": 59,
          "draws": 50,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "enabled",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "meituan/longcat-2.0",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 34,
          "model": "meituan/longcat-2.0",
          "point_rating_method": "sequential_elo",
          "public_id": "E-ef389910f6cc07cc",
          "rated_matches": 143,
          "raw_elo_rating": 1617.7535583908511,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "enabled",
          "repair_status": "first_pass",
          "score": 54.86827170970613,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 59
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 90,
          "capped_draws": 16,
          "coverage_status": "rated",
          "distinct_rated_opponents": 42,
          "draws": 16,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "meta/muse-spark-1.2",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-08-13T16:58:34Z",
          "losses": 19,
          "model": "meta/muse-spark-1.2",
          "point_rating_method": "sequential_elo",
          "public_id": "E-502a038b3a2d63ef",
          "rated_matches": 90,
          "raw_elo_rating": 1697.4882744755037,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 62.06040464059319,
          "uncertainty": 8.664241836095918,
          "unilateral_faults": 0,
          "wins": 55
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 116,
          "capped_draws": 90,
          "coverage_status": "rated",
          "distinct_rated_opponents": 53,
          "draws": 90,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "enabled",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "minimax/minimax-m3",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 19,
          "model": "minimax/minimax-m3",
          "point_rating_method": "sequential_elo",
          "public_id": "E-d169e7b29be70652",
          "rated_matches": 116,
          "raw_elo_rating": 1411.9719926684977,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "enabled",
          "repair_status": "repaired",
          "score": 33.69443719624106,
          "uncertainty": 2.4750163521024238,
          "unilateral_faults": 0,
          "wins": 7
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 98,
          "capped_draws": 10,
          "coverage_status": "rated",
          "distinct_rated_opponents": 45,
          "draws": 10,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "enabled",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "moonshotai/kimi-k2.7-code",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 30,
          "model": "moonshotai/kimi-k2.7-code",
          "point_rating_method": "sequential_elo",
          "public_id": "E-251b5d53a5f89562",
          "rated_matches": 98,
          "raw_elo_rating": 1716.3352365750259,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "enabled",
          "repair_status": "repaired",
          "score": 64.14078623679886,
          "uncertainty": 6.501890762960602,
          "unilateral_faults": 0,
          "wins": 58
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 192,
          "capped_draws": 134,
          "coverage_status": "rated",
          "distinct_rated_opponents": 75,
          "draws": 134,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "moonshotai/kimi-k3",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T14:00:00Z",
          "losses": 46,
          "model": "moonshotai/kimi-k3",
          "point_rating_method": "sequential_elo",
          "public_id": "E-151c4ee6a2d1838e",
          "rated_matches": 192,
          "raw_elo_rating": 1378.0442055713736,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "first_pass",
          "score": 31.092003821784623,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 12
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 92,
          "capped_draws": 13,
          "coverage_status": "rated",
          "distinct_rated_opponents": 44,
          "draws": 13,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "enabled",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "nex-agi/nex-n2-pro",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 71,
          "model": "nex-agi/nex-n2-pro",
          "point_rating_method": "sequential_elo",
          "public_id": "E-92332f4d765b2297",
          "rated_matches": 92,
          "raw_elo_rating": 1194.9426957801345,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "enabled",
          "repair_status": "repaired",
          "score": 11.297346143143717,
          "uncertainty": 8.09758473652126,
          "unilateral_faults": 0,
          "wins": 8
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 110,
          "capped_draws": 74,
          "coverage_status": "rated",
          "distinct_rated_opponents": 55,
          "draws": 74,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "nvidia/nemotron-3-ultra-550b-a55b",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 27,
          "model": "nvidia/nemotron-3-ultra-550b-a55b",
          "point_rating_method": "sequential_elo",
          "public_id": "E-15cf0dede27b7e1b",
          "rated_matches": 110,
          "raw_elo_rating": 1406.0071008564112,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "repaired",
          "score": 32.99164981596408,
          "uncertainty": 3.707899787624953,
          "unilateral_faults": 0,
          "wins": 9
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 124,
          "capped_draws": 63,
          "coverage_status": "rated",
          "distinct_rated_opponents": 61,
          "draws": 63,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "o3",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 32,
          "model": "o3",
          "point_rating_method": "sequential_elo",
          "public_id": "E-35de956c8305ff90",
          "rated_matches": 124,
          "raw_elo_rating": 1463.6955904890767,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 39.04547015939034,
          "uncertainty": 0.9713595499957961,
          "unilateral_faults": 0,
          "wins": 29
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 118,
          "capped_draws": 86,
          "coverage_status": "rated",
          "distinct_rated_opponents": 56,
          "draws": 86,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "openai/gpt-oss-120b",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 23,
          "model": "openai/gpt-oss-120b",
          "point_rating_method": "sequential_elo",
          "public_id": "E-6e65dec497ff2de3",
          "rated_matches": 118,
          "raw_elo_rating": 1421.642551452285,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "repaired",
          "score": 34.70371174356963,
          "uncertainty": 2.084924851410568,
          "unilateral_faults": 0,
          "wins": 9
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 172,
          "capped_draws": 117,
          "coverage_status": "rated",
          "distinct_rated_opponents": 66,
          "draws": 117,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "enabled",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "poolside/laguna-s-2.1",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 48,
          "model": "poolside/laguna-s-2.1",
          "point_rating_method": "sequential_elo",
          "public_id": "E-0fab95afbec0dd98",
          "rated_matches": 172,
          "raw_elo_rating": 1349.8114450883386,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "enabled",
          "repair_status": "first_pass",
          "score": 28.073919300094598,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 7
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 172,
          "capped_draws": 118,
          "coverage_status": "rated",
          "distinct_rated_opponents": 66,
          "draws": 118,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "enabled",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "poolside/laguna-s-2.1",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 47,
          "model": "poolside/laguna-s-2.1",
          "point_rating_method": "sequential_elo",
          "public_id": "E-f72c72b8f264c57a",
          "rated_matches": 172,
          "raw_elo_rating": 1358.3761132030627,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "enabled",
          "repair_status": "first_pass",
          "score": 28.93983337446566,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 7
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 118,
          "capped_draws": 76,
          "coverage_status": "rated",
          "distinct_rated_opponents": 55,
          "draws": 76,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "enabled",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "qwen/qwen3.7-max",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 31,
          "model": "qwen/qwen3.7-max",
          "point_rating_method": "sequential_elo",
          "public_id": "E-64624689e7cbd439",
          "rated_matches": 118,
          "raw_elo_rating": 1440.8004114495486,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "enabled",
          "repair_status": "repaired",
          "score": 36.640629833593636,
          "uncertainty": 2.084924851410568,
          "unilateral_faults": 0,
          "wins": 11
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 114,
          "capped_draws": 94,
          "coverage_status": "rated",
          "distinct_rated_opponents": 54,
          "draws": 94,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "enabled",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "qwen/qwen3.7-plus",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 20,
          "model": "qwen/qwen3.7-plus",
          "point_rating_method": "sequential_elo",
          "public_id": "E-6c2a9942e92223c8",
          "rated_matches": 114,
          "raw_elo_rating": 1415.39305533373,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "enabled",
          "repair_status": "first_pass",
          "score": 34.007945969500966,
          "uncertainty": 2.875240412015687,
          "unilateral_faults": 0,
          "wins": 0
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 18,
          "capped_draws": 5,
          "coverage_status": "under_covered",
          "distinct_rated_opponents": 7,
          "draws": 5,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "qwen/qwen3.8-max",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 2,
          "model": "qwen/qwen3.8-max",
          "point_rating_method": "sequential_elo",
          "public_id": "E-58e68aa5bf529b8a",
          "rated_matches": 18,
          "raw_elo_rating": 1632.9497775865889,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 50.496905291659246,
          "uncertainty": 70.95786693528086,
          "unilateral_faults": 0,
          "wins": 11
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 14,
          "capped_draws": 7,
          "coverage_status": "rated",
          "distinct_rated_opponents": 7,
          "draws": 7,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "stealth/ox-alpha",
            "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-08-22T00:27:26Z",
          "losses": 4,
          "model": "stealth/ox-alpha",
          "point_rating_method": "sequential_elo",
          "public_id": "E-273045858e4a7f82",
          "rated_matches": 14,
          "raw_elo_rating": 1484.4731032493053,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "first_pass",
          "score": 34.32143461607768,
          "uncertainty": 85.34944487358055,
          "unilateral_faults": 0,
          "wins": 3
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 14,
          "capped_draws": 3,
          "coverage_status": "rated",
          "distinct_rated_opponents": 7,
          "draws": 3,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "stealth/ox-alpha",
            "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-08-22T00:27:26Z",
          "losses": 3,
          "model": "stealth/ox-alpha",
          "point_rating_method": "sequential_elo",
          "public_id": "E-8094ab91b5be5ad0",
          "rated_matches": 14,
          "raw_elo_rating": 1563.4373437594195,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "first_pass",
          "score": 42.30496022545644,
          "uncertainty": 85.34944487358055,
          "unilateral_faults": 0,
          "wins": 8
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 14,
          "capped_draws": 7,
          "coverage_status": "rated",
          "distinct_rated_opponents": 7,
          "draws": 7,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "stealth/ox-alpha",
            "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-08-22T00:27:26Z",
          "losses": 6,
          "model": "stealth/ox-alpha",
          "point_rating_method": "sequential_elo",
          "public_id": "E-a87ab54ca8c5ca34",
          "rated_matches": 14,
          "raw_elo_rating": 1444.3642926806658,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "repaired",
          "score": 30.26631150886005,
          "uncertainty": 85.34944487358055,
          "unilateral_faults": 0,
          "wins": 1
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 157,
          "capped_draws": 96,
          "coverage_status": "rated",
          "distinct_rated_opponents": 60,
          "draws": 96,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "thinkingmachines/inkling",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 50,
          "model": "thinkingmachines/inkling",
          "point_rating_method": "sequential_elo",
          "public_id": "E-9f74dab09049a473",
          "rated_matches": 157,
          "raw_elo_rating": 1328.7976684792145,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 25.806720683180234,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 11
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 15,
          "capped_draws": 12,
          "coverage_status": "under_covered",
          "distinct_rated_opponents": 7,
          "draws": 12,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "thinkingmachines/inkling-small",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 3,
          "model": "thinkingmachines/inkling-small",
          "point_rating_method": "sequential_elo",
          "public_id": "E-9cd2fd1302bb65bd",
          "rated_matches": 15,
          "raw_elo_rating": 1460.0832035786366,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 32.187114460064755,
          "uncertainty": 81.25,
          "unilateral_faults": 0,
          "wins": 0
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 102,
          "capped_draws": 1,
          "coverage_status": "rated",
          "distinct_rated_opponents": 51,
          "draws": 1,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "x-ai/grok-4.5",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T14:00:00Z",
          "losses": 14,
          "model": "x-ai/grok-4.5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-73422318071a105c",
          "rated_matches": 102,
          "raw_elo_rating": 1930.9765683598841,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 85.92138340901016,
          "uncertainty": 5.516463908214657,
          "unilateral_faults": 0,
          "wins": 87
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 114,
          "capped_draws": 93,
          "coverage_status": "rated",
          "distinct_rated_opponents": 56,
          "draws": 93,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "enabled",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "x-ai/grok-build-0.1",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 15,
          "model": "x-ai/grok-build-0.1",
          "point_rating_method": "sequential_elo",
          "public_id": "E-3e2fe948d2bcebb0",
          "rated_matches": 114,
          "raw_elo_rating": 1404.4257773948275,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "enabled",
          "repair_status": "repaired",
          "score": 32.89912071233677,
          "uncertainty": 2.875240412015687,
          "unilateral_faults": 0,
          "wins": 6
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 104,
          "capped_draws": 53,
          "coverage_status": "rated",
          "distinct_rated_opponents": 50,
          "draws": 53,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "enabled",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "xiaomi/mimo-v2.5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-03T19:35:00Z",
          "losses": 30,
          "model": "xiaomi/mimo-v2.5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-650d06103e7fa176",
          "rated_matches": 104,
          "raw_elo_rating": 1485.4249105169813,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "enabled",
          "repair_status": "repaired",
          "score": 40.91288442671314,
          "uncertainty": 5.045003647426665,
          "unilateral_faults": 0,
          "wins": 21
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 94,
          "capped_draws": 45,
          "coverage_status": "rated",
          "distinct_rated_opponents": 44,
          "draws": 45,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "xiaomi/mimo-v2.5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T06:10:40Z",
          "losses": 46,
          "model": "xiaomi/mimo-v2.5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-b5eb7da0f5021b69",
          "rated_matches": 94,
          "raw_elo_rating": 1275.0559963930348,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "repaired",
          "score": 19.44142277101602,
          "uncertainty": 7.54891760425771,
          "unilateral_faults": 0,
          "wins": 3
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 102,
          "capped_draws": 75,
          "coverage_status": "rated",
          "distinct_rated_opponents": 48,
          "draws": 75,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "enabled",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "xiaomi/mimo-v2.5-pro",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 25,
          "model": "xiaomi/mimo-v2.5-pro",
          "point_rating_method": "sequential_elo",
          "public_id": "E-bd1bb7ac29877b8f",
          "rated_matches": 102,
          "raw_elo_rating": 1367.9946417839965,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "enabled",
          "repair_status": "repaired",
          "score": 29.00219316035198,
          "uncertainty": 5.516463908214657,
          "unilateral_faults": 0,
          "wins": 2
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 78,
          "capped_draws": 66,
          "coverage_status": "rated",
          "distinct_rated_opponents": 39,
          "draws": 66,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "z-ai/glm-5.2",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-11T17:22:09Z",
          "losses": 11,
          "model": "z-ai/glm-5.2",
          "point_rating_method": "sequential_elo",
          "public_id": "E-da1e9a6be31e371f",
          "rated_matches": 78,
          "raw_elo_rating": 1412.1516499621744,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "repaired",
          "score": 32.90140047086365,
          "uncertainty": 12.5043950463012,
          "unilateral_faults": 0,
          "wins": 1
        }
      ]
    },
    "full_freedom/baseline": {
      "GB2-01": [
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 118,
          "capped_draws": 77,
          "coverage_status": "rated",
          "distinct_rated_opponents": 58,
          "draws": 77,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-opus-4-5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "omitted",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 26,
          "model": "claude-opus-4-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-2e3eca63f7980fac",
          "rated_matches": 118,
          "raw_elo_rating": 1426.0475483689286,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "omitted",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 39.60642935936982,
          "uncertainty": 2.084924851410568,
          "unilateral_faults": 0,
          "wins": 15
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 88,
          "capped_draws": 23,
          "coverage_status": "rated",
          "distinct_rated_opponents": 44,
          "draws": 23,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-opus-4-8",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "omitted",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 24,
          "model": "claude-opus-4-8",
          "point_rating_method": "sequential_elo",
          "public_id": "E-757a6149e87d8b53",
          "rated_matches": 88,
          "raw_elo_rating": 1564.0122470382578,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "omitted",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 52.971032291512834,
          "uncertainty": 9.249894000318006,
          "unilateral_faults": 0,
          "wins": 41
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 122,
          "capped_draws": 89,
          "coverage_status": "rated",
          "distinct_rated_opponents": 59,
          "draws": 89,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-opus-5",
            "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-25T15:48:00Z",
          "losses": 14,
          "model": "claude-opus-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-6c30dc38efb07e9e",
          "rated_matches": 121,
          "raw_elo_rating": 1541.7900362821504,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 51.350232950765154,
          "uncertainty": 1.5178730212592662,
          "unilateral_faults": 0,
          "wins": 18
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 120,
          "capped_draws": 16,
          "coverage_status": "rated",
          "distinct_rated_opponents": 58,
          "draws": 16,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-opus-5",
            "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-25T15:48:00Z",
          "losses": 9,
          "model": "claude-opus-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-865d68ab219fd7ee",
          "rated_matches": 120,
          "raw_elo_rating": 1893.5408887472404,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 86.8861767990556,
          "uncertainty": 1.7045454545454586,
          "unilateral_faults": 0,
          "wins": 95
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 178,
          "capped_draws": 128,
          "coverage_status": "rated",
          "distinct_rated_opponents": 65,
          "draws": 128,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "unknown_legacy",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-sonnet-5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "unknown_legacy",
            "request_mode": "unknown_legacy",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-12T16:00:00Z",
          "losses": 36,
          "model": "claude-sonnet-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-259fc4a9e48c81f2",
          "rated_matches": 178,
          "raw_elo_rating": 1387.0397820883597,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 36.3482511329046,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 14
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 114,
          "capped_draws": 26,
          "coverage_status": "rated",
          "distinct_rated_opponents": 56,
          "draws": 26,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-sonnet-5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 35,
          "model": "claude-sonnet-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-73ff84eba4ec19cb",
          "rated_matches": 114,
          "raw_elo_rating": 1598.8545648282711,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 57.007926489898445,
          "uncertainty": 2.875240412015687,
          "unilateral_faults": 0,
          "wins": 53
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 89,
          "capped_draws": 16,
          "coverage_status": "rated",
          "distinct_rated_opponents": 42,
          "draws": 16,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-sonnet-5",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 45,
          "model": "claude-sonnet-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-93cff8e6feb76995",
          "rated_matches": 89,
          "raw_elo_rating": 1471.9176789585542,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 43.687018397883946,
          "uncertainty": 8.954627669472988,
          "unilateral_faults": 0,
          "wins": 28
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 128,
          "capped_draws": 77,
          "coverage_status": "rated",
          "distinct_rated_opponents": 59,
          "draws": 77,
          "evaluated_setting_identity": {
            "canonical_provider_route": "unknown_legacy",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "cohere/north-mini-code:free",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 30,
          "model": "cohere/north-mini-code",
          "point_rating_method": "sequential_elo",
          "public_id": "E-194759b182ce3244",
          "rated_matches": 128,
          "raw_elo_rating": 1489.189872373205,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 46.13468842367974,
          "uncertainty": 0.27254531628119416,
          "unilateral_faults": 0,
          "wins": 21
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 98,
          "capped_draws": 21,
          "coverage_status": "rated",
          "distinct_rated_opponents": 47,
          "draws": 21,
          "evaluated_setting_identity": {
            "canonical_provider_route": "unknown_legacy",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "cohere/north-mini-code:free",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-11T17:22:09Z",
          "losses": 75,
          "model": "cohere/north-mini-code",
          "point_rating_method": "sequential_elo",
          "public_id": "E-c309b463b29efb71",
          "rated_matches": 98,
          "raw_elo_rating": 1037.886145799525,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "none",
          "repair_status": "repaired",
          "score": 0.018287462616778865,
          "uncertainty": 6.501890762960602,
          "unilateral_faults": 0,
          "wins": 2
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 128,
          "capped_draws": 46,
          "coverage_status": "rated",
          "distinct_rated_opponents": 62,
          "draws": 46,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "deepseek/deepseek-v4-pro",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 48,
          "model": "deepseek/deepseek-v4-pro",
          "point_rating_method": "sequential_elo",
          "public_id": "E-e121525dd1846069",
          "rated_matches": 128,
          "raw_elo_rating": 1453.1514954467345,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 42.49233284225822,
          "uncertainty": 0.27254531628119416,
          "unilateral_faults": 0,
          "wins": 34
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 76,
          "capped_draws": 25,
          "coverage_status": "rated",
          "distinct_rated_opponents": 38,
          "draws": 25,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "google/gemini-3.1-flash-lite",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 45,
          "model": "google/gemini-3.1-flash-lite",
          "point_rating_method": "sequential_elo",
          "public_id": "E-cc0af0bfa6a9a29f",
          "rated_matches": 76,
          "raw_elo_rating": 1144.1569784358514,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "repaired",
          "score": 10.214928346057336,
          "uncertainty": 13.230288229818967,
          "unilateral_faults": 0,
          "wins": 6
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 0,
          "capped_draws": 0,
          "coverage_status": "pending",
          "distinct_rated_opponents": 0,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "low",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "google/gemini-3.5-flash",
            "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-21T14:20:15Z",
          "losses": 0,
          "model": "google/gemini-3.5-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-b33eea8b864e22bf",
          "rated_matches": 0,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "low",
          "repair_status": "first_pass",
          "unilateral_faults": 0,
          "wins": 0
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 178,
          "capped_draws": 44,
          "coverage_status": "rated",
          "distinct_rated_opponents": 68,
          "draws": 44,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "minimal",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "google/gemini-3.5-flash-lite",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 72,
          "model": "google/gemini-3.5-flash-lite",
          "point_rating_method": "sequential_elo",
          "public_id": "E-21c0edac8ac36f2e",
          "rated_matches": 178,
          "raw_elo_rating": 1370.3859439113394,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "minimal",
          "repair_status": "first_pass",
          "score": 34.66506765991066,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 62
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 176,
          "capped_draws": 39,
          "coverage_status": "rated",
          "distinct_rated_opponents": 66,
          "draws": 39,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "minimal",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "google/gemini-3.5-flash-lite",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 88,
          "model": "google/gemini-3.5-flash-lite",
          "point_rating_method": "sequential_elo",
          "public_id": "E-cf51875df5447bc2",
          "rated_matches": 176,
          "raw_elo_rating": 1406.3241755085214,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "minimal",
          "repair_status": "first_pass",
          "score": 38.28027790563501,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 49
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 174,
          "capped_draws": 48,
          "coverage_status": "rated",
          "distinct_rated_opponents": 65,
          "draws": 48,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "minimal",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "google/gemini-3.6-flash",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 92,
          "model": "google/gemini-3.6-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-e0c4f14c94c0a42a",
          "rated_matches": 174,
          "raw_elo_rating": 1192.2933088137934,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "minimal",
          "repair_status": "first_pass",
          "score": 16.631119845397098,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 34
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 174,
          "capped_draws": 34,
          "coverage_status": "rated",
          "distinct_rated_opponents": 66,
          "draws": 34,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "minimal",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "google/gemini-3.6-flash",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 94,
          "model": "google/gemini-3.6-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-e9733de94d982ade",
          "rated_matches": 174,
          "raw_elo_rating": 1322.3387367350888,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "minimal",
          "repair_status": "first_pass",
          "score": 29.774655448954377,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 46
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 120,
          "capped_draws": 25,
          "coverage_status": "rated",
          "distinct_rated_opponents": 58,
          "draws": 25,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "google/gemma-4-31b-it",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 40,
          "model": "google/gemma-4-31b-it",
          "point_rating_method": "sequential_elo",
          "public_id": "E-caaa54d3c88e6570",
          "rated_matches": 120,
          "raw_elo_rating": 1453.704251657997,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 42.432414819587265,
          "uncertainty": 1.7045454545454586,
          "unilateral_faults": 0,
          "wins": 55
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 114,
          "capped_draws": 5,
          "coverage_status": "rated",
          "distinct_rated_opponents": 56,
          "draws": 5,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-4.1",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "omitted",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 49,
          "model": "gpt-4.1",
          "point_rating_method": "sequential_elo",
          "public_id": "E-f50ec6b60d5b85da",
          "rated_matches": 113,
          "raw_elo_rating": 1572.9878368669815,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "omitted",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 54.37710879884957,
          "uncertainty": 3.079290579084697,
          "unilateral_faults": 1,
          "wins": 59
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 168,
          "capped_draws": 39,
          "coverage_status": "rated",
          "distinct_rated_opponents": 63,
          "draws": 39,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-4.1-nano",
            "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "omitted",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-12T16:00:00Z",
          "losses": 69,
          "model": "gpt-4.1-nano",
          "point_rating_method": "sequential_elo",
          "public_id": "E-e117cfcfd3d0bf38",
          "rated_matches": 168,
          "raw_elo_rating": 1429.1019623450045,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "omitted",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 40.511310783890416,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 60
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 0,
          "capped_draws": 0,
          "coverage_status": "pending",
          "distinct_rated_opponents": 0,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "low",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5",
            "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-21T14:20:15Z",
          "losses": 0,
          "model": "gpt-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-4370194a9beec334",
          "rated_matches": 0,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "low",
          "repair_status": "first_pass",
          "unilateral_faults": 0,
          "wins": 0
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 102,
          "capped_draws": 2,
          "coverage_status": "rated",
          "distinct_rated_opponents": 48,
          "draws": 2,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.4",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 6,
          "model": "gpt-5.4",
          "point_rating_method": "sequential_elo",
          "public_id": "E-60fa13e461853992",
          "rated_matches": 96,
          "raw_elo_rating": 2013.7931496605154,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 98.61036508816744,
          "uncertainty": 7.017308256680951,
          "unilateral_faults": 0,
          "wins": 88
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 96,
          "capped_draws": 4,
          "coverage_status": "rated",
          "distinct_rated_opponents": 42,
          "draws": 4,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.4",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 20,
          "model": "gpt-5.4",
          "point_rating_method": "sequential_elo",
          "public_id": "E-ed2ff19b1858f2c4",
          "rated_matches": 96,
          "raw_elo_rating": 1767.2477663915254,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 73.69231856637961,
          "uncertainty": 7.017308256680951,
          "unilateral_faults": 0,
          "wins": 72
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 108,
          "capped_draws": 40,
          "coverage_status": "rated",
          "distinct_rated_opponents": 53,
          "draws": 40,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.4-mini",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 46,
          "model": "gpt-5.4-mini",
          "point_rating_method": "sequential_elo",
          "public_id": "E-ea1cb793f92b3cff",
          "rated_matches": 108,
          "raw_elo_rating": 1351.113886438586,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 31.866704468526944,
          "uncertainty": 4.1413142610575715,
          "unilateral_faults": 0,
          "wins": 22
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 90,
          "capped_draws": 19,
          "coverage_status": "rated",
          "distinct_rated_opponents": 44,
          "draws": 19,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.4-nano",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-09T17:30:50Z",
          "losses": 24,
          "model": "gpt-5.4-nano",
          "point_rating_method": "sequential_elo",
          "public_id": "E-9eb27042bf28d67c",
          "rated_matches": 90,
          "raw_elo_rating": 1599.004624163251,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 56.55502285621712,
          "uncertainty": 8.664241836095918,
          "unilateral_faults": 0,
          "wins": 47
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 112,
          "capped_draws": 35,
          "coverage_status": "rated",
          "distinct_rated_opponents": 52,
          "draws": 35,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.4-nano",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 38,
          "model": "gpt-5.4-nano",
          "point_rating_method": "sequential_elo",
          "public_id": "E-a8887794a1195b75",
          "rated_matches": 106,
          "raw_elo_rating": 1540.976761634146,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "repaired",
          "score": 51.01989606082149,
          "uncertainty": 4.586824452283178,
          "unilateral_faults": 0,
          "wins": 33
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 122,
          "capped_draws": 92,
          "coverage_status": "rated",
          "distinct_rated_opponents": 60,
          "draws": 92,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 19,
          "model": "gpt-5.5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-58178b9b32a94ca0",
          "rated_matches": 122,
          "raw_elo_rating": 1507.7226018234821,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 47.92198712859516,
          "uncertainty": 1.3334817333716131,
          "unilateral_faults": 0,
          "wins": 11
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 91,
          "capped_draws": 14,
          "coverage_status": "rated",
          "distinct_rated_opponents": 43,
          "draws": 14,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.6-luna",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 68,
          "model": "gpt-5.6-luna",
          "point_rating_method": "sequential_elo",
          "public_id": "E-9502190155453416",
          "rated_matches": 91,
          "raw_elo_rating": 1231.009568848009,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 19.385298777703543,
          "uncertainty": 8.378603514268699,
          "unilateral_faults": 0,
          "wins": 9
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 102,
          "capped_draws": 30,
          "coverage_status": "rated",
          "distinct_rated_opponents": 49,
          "draws": 30,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.6-luna",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-10T05:30:29Z",
          "losses": 55,
          "model": "gpt-5.6-luna",
          "point_rating_method": "sequential_elo",
          "public_id": "E-959ed218b1c5605b",
          "rated_matches": 99,
          "raw_elo_rating": 1231.2408205466734,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 19.58077943551401,
          "uncertainty": 6.25,
          "unilateral_faults": 0,
          "wins": 14
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 90,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 42,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.6-sol",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 20,
          "model": "gpt-5.6-sol",
          "point_rating_method": "sequential_elo",
          "public_id": "E-72b9641e74736185",
          "rated_matches": 90,
          "raw_elo_rating": 1820.9424671159038,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 78.9860147584493,
          "uncertainty": 8.664241836095918,
          "unilateral_faults": 0,
          "wins": 70
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 96,
          "capped_draws": 12,
          "coverage_status": "rated",
          "distinct_rated_opponents": 45,
          "draws": 12,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.6-sol",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-10T05:30:29Z",
          "losses": 30,
          "model": "gpt-5.6-sol",
          "point_rating_method": "sequential_elo",
          "public_id": "E-890c38b8e811c121",
          "rated_matches": 90,
          "raw_elo_rating": 1536.020997495056,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 50.18934316422834,
          "uncertainty": 8.664241836095918,
          "unilateral_faults": 0,
          "wins": 48
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 98,
          "capped_draws": 30,
          "coverage_status": "rated",
          "distinct_rated_opponents": 48,
          "draws": 30,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.6-terra",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-10T05:30:29Z",
          "losses": 39,
          "model": "gpt-5.6-terra",
          "point_rating_method": "sequential_elo",
          "public_id": "E-40742129939a44b5",
          "rated_matches": 98,
          "raw_elo_rating": 1546.0809635791695,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 51.380928870298845,
          "uncertainty": 6.501890762960602,
          "unilateral_faults": 0,
          "wins": 29
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 158,
          "capped_draws": 58,
          "coverage_status": "rated",
          "distinct_rated_opponents": 61,
          "draws": 58,
          "evaluated_setting_identity": {
            "canonical_provider_route": "unknown_legacy",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "inclusionai/ling-3.0-flash:free",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 49,
          "model": "inclusionai/ling-3.0-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-3c618b88b6bdb039",
          "rated_matches": 158,
          "raw_elo_rating": 1323.2806115247317,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 29.719771976725053,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 51
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 156,
          "capped_draws": 43,
          "coverage_status": "rated",
          "distinct_rated_opponents": 56,
          "draws": 43,
          "evaluated_setting_identity": {
            "canonical_provider_route": "unknown_legacy",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "inclusionai/ling-3.0-flash:free",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 71,
          "model": "inclusionai/ling-3.0-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-f9af396559c3a1cd",
          "rated_matches": 156,
          "raw_elo_rating": 1446.8012623161792,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 42.18349970806349,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 42
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 116,
          "capped_draws": 34,
          "coverage_status": "rated",
          "distinct_rated_opponents": 55,
          "draws": 34,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "meituan/longcat-2.0",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 48,
          "model": "meituan/longcat-2.0",
          "point_rating_method": "sequential_elo",
          "public_id": "E-9f5585b5fd96f2c3",
          "rated_matches": 116,
          "raw_elo_rating": 1389.7867858370455,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 35.91005666671926,
          "uncertainty": 2.4750163521024238,
          "unilateral_faults": 0,
          "wins": 34
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 126,
          "capped_draws": 48,
          "coverage_status": "rated",
          "distinct_rated_opponents": 60,
          "draws": 48,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "meituan/longcat-2.0",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 47,
          "model": "meituan/longcat-2.0",
          "point_rating_method": "sequential_elo",
          "public_id": "E-ed0f8e084958eebc",
          "rated_matches": 126,
          "raw_elo_rating": 1326.9943345633974,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 29.713862088769478,
          "uncertainty": 0.617825470805693,
          "unilateral_faults": 0,
          "wins": 31
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 92,
          "capped_draws": 39,
          "coverage_status": "rated",
          "distinct_rated_opponents": 43,
          "draws": 39,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "minimal",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "meta/muse-spark-1.2",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-08-13T16:58:34Z",
          "losses": 44,
          "model": "meta/muse-spark-1.2",
          "point_rating_method": "sequential_elo",
          "public_id": "E-d883d9ce56d6c656",
          "rated_matches": 92,
          "raw_elo_rating": 1367.3882021779489,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "minimal",
          "repair_status": "first_pass",
          "score": 33.19164564959547,
          "uncertainty": 8.09758473652126,
          "unilateral_faults": 0,
          "wins": 9
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 124,
          "capped_draws": 24,
          "coverage_status": "rated",
          "distinct_rated_opponents": 61,
          "draws": 24,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "minimax/minimax-m3",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 40,
          "model": "minimax/minimax-m3",
          "point_rating_method": "sequential_elo",
          "public_id": "E-444510032bc433fc",
          "rated_matches": 124,
          "raw_elo_rating": 1518.7090711594628,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 49.061655826617994,
          "uncertainty": 0.9713595499957961,
          "unilateral_faults": 0,
          "wins": 60
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 136,
          "capped_draws": 9,
          "coverage_status": "rated",
          "distinct_rated_opponents": 50,
          "draws": 9,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "mistralai/mistral-medium-3-5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 49,
          "model": "mistralai/mistral-medium-3-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-a0a38f5e77e983bc",
          "rated_matches": 101,
          "raw_elo_rating": 1431.8243444955588,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "repaired",
          "score": 39.8933469399602,
          "uncertainty": 5.757377148833722,
          "unilateral_faults": 35,
          "wins": 43
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 203,
          "capped_draws": 139,
          "coverage_status": "rated",
          "distinct_rated_opponents": 79,
          "draws": 139,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "low",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "moonshotai/kimi-k3",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T14:00:00Z",
          "losses": 32,
          "model": "moonshotai/kimi-k3",
          "point_rating_method": "sequential_elo",
          "public_id": "E-fb8801908d28001f",
          "rated_matches": 203,
          "raw_elo_rating": 1477.9678850754415,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "low",
          "repair_status": "first_pass",
          "score": 45.72944773324043,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 32
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 86,
          "capped_draws": 14,
          "coverage_status": "rated",
          "distinct_rated_opponents": 43,
          "draws": 14,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "nvidia/nemotron-3-ultra-550b-a55b",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 44,
          "model": "nvidia/nemotron-3-ultra-550b-a55b",
          "point_rating_method": "sequential_elo",
          "public_id": "E-0ce5e196701b51f3",
          "rated_matches": 86,
          "raw_elo_rating": 1564.6985011257657,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 52.991414623983445,
          "uncertainty": 9.855626741889738,
          "unilateral_faults": 0,
          "wins": 28
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 166,
          "capped_draws": 48,
          "coverage_status": "rated",
          "distinct_rated_opponents": 62,
          "draws": 48,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "low",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "o3",
            "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-21T14:20:15Z",
          "losses": 111,
          "model": "o3",
          "point_rating_method": "sequential_elo",
          "public_id": "E-cb2bd51b4adfa607",
          "rated_matches": 166,
          "raw_elo_rating": 1105.068326196998,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "low",
          "repair_status": "first_pass",
          "score": 7.743053185185025,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 7
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 176,
          "capped_draws": 35,
          "coverage_status": "rated",
          "distinct_rated_opponents": 70,
          "draws": 35,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "low",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "openai/gpt-oss-120b",
            "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-21T14:20:15Z",
          "losses": 113,
          "model": "openai/gpt-oss-120b",
          "point_rating_method": "sequential_elo",
          "public_id": "E-55f6c0e3dc8a8065",
          "rated_matches": 176,
          "raw_elo_rating": 1217.332032382236,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "low",
          "repair_status": "first_pass",
          "score": 19.17906841539228,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 28
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 122,
          "capped_draws": 20,
          "coverage_status": "rated",
          "distinct_rated_opponents": 60,
          "draws": 20,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "poolside/laguna-s-2.1",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 61,
          "model": "poolside/laguna-s-2.1",
          "point_rating_method": "sequential_elo",
          "public_id": "E-8461eb1b16e40129",
          "rated_matches": 122,
          "raw_elo_rating": 1543.463623200794,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "none",
          "repair_status": "repaired",
          "score": 51.53428934089981,
          "uncertainty": 1.3334817333716131,
          "unilateral_faults": 0,
          "wins": 41
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 118,
          "capped_draws": 34,
          "coverage_status": "rated",
          "distinct_rated_opponents": 56,
          "draws": 34,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "poolside/laguna-s-2.1",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 47,
          "model": "poolside/laguna-s-2.1",
          "point_rating_method": "sequential_elo",
          "public_id": "E-c58ec61528547516",
          "rated_matches": 118,
          "raw_elo_rating": 1410.5416079468907,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 38.039262537272585,
          "uncertainty": 2.084924851410568,
          "unilateral_faults": 0,
          "wins": 37
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 106,
          "capped_draws": 27,
          "coverage_status": "rated",
          "distinct_rated_opponents": 50,
          "draws": 27,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "qwen/qwen3.7-max",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 30,
          "model": "qwen/qwen3.7-max",
          "point_rating_method": "sequential_elo",
          "public_id": "E-8a70cd704fcbcf6f",
          "rated_matches": 100,
          "raw_elo_rating": 1573.513576219901,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 54.19394021291321,
          "uncertainty": 6.001859510499461,
          "unilateral_faults": 0,
          "wins": 43
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 100,
          "capped_draws": 26,
          "coverage_status": "rated",
          "distinct_rated_opponents": 49,
          "draws": 26,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "qwen/qwen3.7-plus",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-03T18:55:00Z",
          "losses": 55,
          "model": "qwen/qwen3.7-plus",
          "point_rating_method": "sequential_elo",
          "public_id": "E-5e09f0c994a59f3c",
          "rated_matches": 100,
          "raw_elo_rating": 1300.7914998768108,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "none",
          "repair_status": "repaired",
          "score": 26.630246682212057,
          "uncertainty": 6.001859510499461,
          "unilateral_faults": 0,
          "wins": 19
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 16,
          "capped_draws": 1,
          "coverage_status": "under_covered",
          "distinct_rated_opponents": 9,
          "draws": 1,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "minimal",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "qwen/qwen3.8-max",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 13,
          "model": "qwen/qwen3.8-max",
          "point_rating_method": "sequential_elo",
          "public_id": "E-60f1c4442483d5b0",
          "rated_matches": 16,
          "raw_elo_rating": 1364.0547383269693,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "minimal",
          "repair_status": "first_pass",
          "score": 27.24176104741712,
          "uncertainty": 77.5178125181665,
          "unilateral_faults": 0,
          "wins": 2
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 14,
          "capped_draws": 2,
          "coverage_status": "rated",
          "distinct_rated_opponents": 7,
          "draws": 2,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "low",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "stealth/ox-alpha",
            "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-08-22T00:27:26Z",
          "losses": 4,
          "model": "stealth/ox-alpha",
          "point_rating_method": "sequential_elo",
          "public_id": "E-5661caf556b12391",
          "rated_matches": 14,
          "raw_elo_rating": 1544.9909685045918,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "low",
          "repair_status": "repaired",
          "score": 44.89554210725235,
          "uncertainty": 85.34944487358055,
          "unilateral_faults": 0,
          "wins": 8
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 14,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 7,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "low",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "stealth/ox-alpha",
            "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-08-22T00:27:26Z",
          "losses": 12,
          "model": "stealth/ox-alpha",
          "point_rating_method": "sequential_elo",
          "public_id": "E-98157b387f582b30",
          "rated_matches": 14,
          "raw_elo_rating": 1375.4345756977473,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "low",
          "repair_status": "repaired",
          "score": 27.758680617463924,
          "uncertainty": 85.34944487358055,
          "unilateral_faults": 0,
          "wins": 2
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 14,
          "capped_draws": 1,
          "coverage_status": "rated",
          "distinct_rated_opponents": 7,
          "draws": 1,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "low",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "stealth/ox-alpha",
            "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-08-22T00:27:26Z",
          "losses": 11,
          "model": "stealth/ox-alpha",
          "point_rating_method": "sequential_elo",
          "public_id": "E-e66ff5a9cbd5132f",
          "rated_matches": 14,
          "raw_elo_rating": 1396.0549803844092,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "low",
          "repair_status": "first_pass",
          "score": 29.842760215578874,
          "uncertainty": 85.34944487358055,
          "unilateral_faults": 0,
          "wins": 2
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 106,
          "capped_draws": 18,
          "coverage_status": "rated",
          "distinct_rated_opponents": 50,
          "draws": 18,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "tencent/hy3-preview",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 19,
          "model": "tencent/hy3-preview",
          "point_rating_method": "sequential_elo",
          "public_id": "E-3407ff2dd1928eb5",
          "rated_matches": 100,
          "raw_elo_rating": 1740.5175222083988,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 71.07282896064237,
          "uncertainty": 6.001859510499461,
          "unilateral_faults": 0,
          "wins": 63
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 116,
          "capped_draws": 51,
          "coverage_status": "rated",
          "distinct_rated_opponents": 55,
          "draws": 51,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "thinkingmachines/inkling",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 49,
          "model": "thinkingmachines/inkling",
          "point_rating_method": "sequential_elo",
          "public_id": "E-9e638fc0ac98df4f",
          "rated_matches": 116,
          "raw_elo_rating": 1225.1596954073368,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 19.271393862806924,
          "uncertainty": 2.4750163521024238,
          "unilateral_faults": 0,
          "wins": 16
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 114,
          "capped_draws": 33,
          "coverage_status": "rated",
          "distinct_rated_opponents": 54,
          "draws": 33,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "thinkingmachines/inkling",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 75,
          "model": "thinkingmachines/inkling",
          "point_rating_method": "sequential_elo",
          "public_id": "E-bc7c657b08ebac66",
          "rated_matches": 114,
          "raw_elo_rating": 1093.3154458051438,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 5.913693373969095,
          "uncertainty": 2.875240412015687,
          "unilateral_faults": 0,
          "wins": 6
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 19,
          "capped_draws": 3,
          "coverage_status": "under_covered",
          "distinct_rated_opponents": 9,
          "draws": 3,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "thinkingmachines/inkling-small",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 7,
          "model": "thinkingmachines/inkling-small",
          "point_rating_method": "sequential_elo",
          "public_id": "E-52cb66309e46f2f3",
          "rated_matches": 19,
          "raw_elo_rating": 1494.0445342877708,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 41.144919554096006,
          "uncertainty": 68.05339887498948,
          "unilateral_faults": 0,
          "wins": 9
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 209,
          "capped_draws": 134,
          "coverage_status": "rated",
          "distinct_rated_opponents": 80,
          "draws": 134,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "low",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "x-ai/grok-4.5",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T14:00:00Z",
          "losses": 36,
          "model": "x-ai/grok-4.5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-7ee1b68d1249ac22",
          "rated_matches": 209,
          "raw_elo_rating": 1475.140841118312,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "low",
          "repair_status": "first_pass",
          "score": 45.4844504231055,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 39
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 94,
          "capped_draws": 7,
          "coverage_status": "rated",
          "distinct_rated_opponents": 47,
          "draws": 7,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "xiaomi/mimo-v2.5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T06:10:40Z",
          "losses": 40,
          "model": "xiaomi/mimo-v2.5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-2cdd8ae895784956",
          "rated_matches": 94,
          "raw_elo_rating": 1599.2443785426199,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 56.66943413125931,
          "uncertainty": 7.54891760425771,
          "unilateral_faults": 0,
          "wins": 47
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 120,
          "capped_draws": 27,
          "coverage_status": "rated",
          "distinct_rated_opponents": 59,
          "draws": 27,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "xiaomi/mimo-v2.5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 51,
          "model": "xiaomi/mimo-v2.5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-912a4a40bbdcbd45",
          "rated_matches": 120,
          "raw_elo_rating": 1488.5178228047191,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 45.95098074818603,
          "uncertainty": 1.7045454545454586,
          "unilateral_faults": 0,
          "wins": 42
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 100,
          "capped_draws": 29,
          "coverage_status": "rated",
          "distinct_rated_opponents": 50,
          "draws": 29,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "xiaomi/mimo-v2.5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-01T00:15:48Z",
          "losses": 43,
          "model": "xiaomi/mimo-v2.5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-a168350bd057f924",
          "rated_matches": 100,
          "raw_elo_rating": 1398.495256527627,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 36.50504831628788,
          "uncertainty": 6.001859510499461,
          "unilateral_faults": 0,
          "wins": 28
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 116,
          "capped_draws": 32,
          "coverage_status": "rated",
          "distinct_rated_opponents": 57,
          "draws": 32,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "xiaomi/mimo-v2.5-pro",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 51,
          "model": "xiaomi/mimo-v2.5-pro",
          "point_rating_method": "sequential_elo",
          "public_id": "E-9ce4191c7f1f3b3e",
          "rated_matches": 116,
          "raw_elo_rating": 1402.395743836614,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 37.18442894600758,
          "uncertainty": 2.4750163521024238,
          "unilateral_faults": 0,
          "wins": 33
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 82,
          "capped_draws": 26,
          "coverage_status": "rated",
          "distinct_rated_opponents": 41,
          "draws": 26,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "z-ai/glm-5.2",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-11T14:00:45Z",
          "losses": 27,
          "model": "z-ai/glm-5.2",
          "point_rating_method": "sequential_elo",
          "public_id": "E-5c3b7f5666a38043",
          "rated_matches": 82,
          "raw_elo_rating": 1449.4233859714943,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 41.23748511312021,
          "uncertainty": 11.132129994845172,
          "unilateral_faults": 0,
          "wins": 29
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 74,
          "capped_draws": 3,
          "coverage_status": "rated",
          "distinct_rated_opponents": 37,
          "draws": 3,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "z-ai/glm-5.2",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 49,
          "model": "z-ai/glm-5.2",
          "point_rating_method": "sequential_elo",
          "public_id": "E-c8076ea61de8da45",
          "rated_matches": 74,
          "raw_elo_rating": 1201.6984567131585,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 15.969552191859187,
          "uncertainty": 13.985026918962571,
          "unilateral_faults": 0,
          "wins": 22
        }
      ],
      "GB2-02": [
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 94,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 47,
          "draws": 78,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-opus-4-5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "omitted",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 11,
          "model": "claude-opus-4-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-16462f3d1f3a7b19",
          "rated_matches": 94,
          "raw_elo_rating": 1488.645381413465,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "omitted",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 25.52082770903801,
          "uncertainty": 7.54891760425771,
          "unilateral_faults": 0,
          "wins": 5
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 76,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 37,
          "draws": 68,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-opus-4-8",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "omitted",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 5,
          "model": "claude-opus-4-8",
          "point_rating_method": "sequential_elo",
          "public_id": "E-c142942f4138c871",
          "rated_matches": 76,
          "raw_elo_rating": 1462.7697346783725,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "omitted",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 18.694108648166214,
          "uncertainty": 13.230288229818967,
          "unilateral_faults": 0,
          "wins": 3
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 94,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 47,
          "draws": 26,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-opus-5",
            "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-25T10:50:00Z",
          "losses": 10,
          "model": "claude-opus-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-51ddad48e10b006f",
          "rated_matches": 94,
          "raw_elo_rating": 1672.997271856207,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 66.89123587588573,
          "uncertainty": 7.54891760425771,
          "unilateral_faults": 0,
          "wins": 58
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 92,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 46,
          "draws": 50,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-opus-5",
            "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-25T10:50:00Z",
          "losses": 4,
          "model": "claude-opus-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-772d1a710082ddb3",
          "rated_matches": 92,
          "raw_elo_rating": 1635.8038282071802,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 58.44615398538018,
          "uncertainty": 8.09758473652126,
          "unilateral_faults": 0,
          "wins": 38
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 70,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 32,
          "draws": 61,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-sonnet-5",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 8,
          "model": "claude-sonnet-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-b46bdcad35bcea1d",
          "rated_matches": 70,
          "raw_elo_rating": 1463.6081174048713,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 18.458780422070696,
          "uncertainty": 15.58908290969266,
          "unilateral_faults": 0,
          "wins": 1
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 94,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 47,
          "draws": 81,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-sonnet-5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 10,
          "model": "claude-sonnet-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-e501d6808bd19ccc",
          "rated_matches": 94,
          "raw_elo_rating": 1480.840389816271,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 23.76930952639686,
          "uncertainty": 7.54891760425771,
          "unilateral_faults": 0,
          "wins": 3
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 84,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 42,
          "draws": 80,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "deepseek/deepseek-v4-flash",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 3,
          "model": "deepseek/deepseek-v4-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-3358fbcda6ab6f4d",
          "rated_matches": 84,
          "raw_elo_rating": 1462.6834789339953,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 19.168036379032152,
          "uncertainty": 10.482614454664043,
          "unilateral_faults": 0,
          "wins": 1
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 88,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 44,
          "draws": 80,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "deepseek/deepseek-v4-pro",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 6,
          "model": "deepseek/deepseek-v4-pro",
          "point_rating_method": "sequential_elo",
          "public_id": "E-6c3b019c1b20a09b",
          "rated_matches": 88,
          "raw_elo_rating": 1473.8446177830178,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 21.894015414373516,
          "uncertainty": 9.249894000318006,
          "unilateral_faults": 0,
          "wins": 2
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 62,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 31,
          "draws": 59,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "google/gemini-3.1-flash-lite",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 2,
          "model": "google/gemini-3.1-flash-lite",
          "point_rating_method": "sequential_elo",
          "public_id": "E-20b3484be872df52",
          "rated_matches": 62,
          "raw_elo_rating": 1477.5240632772964,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "repaired",
          "score": 20.925483752639348,
          "uncertainty": 19.244078834871203,
          "unilateral_faults": 0,
          "wins": 1
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 126,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 48,
          "draws": 112,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "minimal",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "google/gemini-3.5-flash-lite",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 12,
          "model": "google/gemini-3.5-flash-lite",
          "point_rating_method": "sequential_elo",
          "public_id": "E-1010911d64a09b68",
          "rated_matches": 126,
          "raw_elo_rating": 1459.4460310730938,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "minimal",
          "repair_status": "repaired",
          "score": 20.212526552183117,
          "uncertainty": 0.617825470805693,
          "unilateral_faults": 0,
          "wins": 2
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 130,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 49,
          "draws": 122,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "minimal",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "google/gemini-3.5-flash-lite",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 8,
          "model": "google/gemini-3.5-flash-lite",
          "point_rating_method": "sequential_elo",
          "public_id": "E-e65fdcb71f09a611",
          "rated_matches": 130,
          "raw_elo_rating": 1452.8690750388523,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "minimal",
          "repair_status": "repaired",
          "score": 18.859141711297916,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 0
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 122,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 47,
          "draws": 111,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "minimal",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "google/gemini-3.6-flash",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 10,
          "model": "google/gemini-3.6-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-4492f6d65cd6280b",
          "rated_matches": 122,
          "raw_elo_rating": 1442.864101000397,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "minimal",
          "repair_status": "first_pass",
          "score": 16.362895246809455,
          "uncertainty": 1.3334817333716131,
          "unilateral_faults": 0,
          "wins": 1
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 130,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 47,
          "draws": 118,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "minimal",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "google/gemini-3.6-flash",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 12,
          "model": "google/gemini-3.6-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-9c8b43dc41bad760",
          "rated_matches": 130,
          "raw_elo_rating": 1448.0725924193703,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "minimal",
          "repair_status": "repaired",
          "score": 17.782763035404734,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 0
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 86,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 43,
          "draws": 72,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-4.1",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "omitted",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 12,
          "model": "gpt-4.1",
          "point_rating_method": "sequential_elo",
          "public_id": "E-e4707b8e4c581ede",
          "rated_matches": 86,
          "raw_elo_rating": 1460.2386314581393,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "omitted",
          "reasoning_setting": "none",
          "repair_status": "repaired",
          "score": 18.7319500025143,
          "uncertainty": 9.855626741889738,
          "unilateral_faults": 0,
          "wins": 2
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 0,
          "capped_draws": 0,
          "coverage_status": "pending",
          "distinct_rated_opponents": 0,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "low",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5",
            "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-21T14:20:15Z",
          "losses": 0,
          "model": "gpt-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-4f8f0a47f75ab6b7",
          "rated_matches": 0,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "low",
          "repair_status": "first_pass",
          "unilateral_faults": 0,
          "wins": 0
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 72,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 31,
          "draws": 61,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.4",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 10,
          "model": "gpt-5.4",
          "point_rating_method": "sequential_elo",
          "public_id": "E-89c7c830b0d1a5cf",
          "rated_matches": 72,
          "raw_elo_rating": 1458.3461864208352,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 17.424895818830112,
          "uncertainty": 14.770573598065289,
          "unilateral_faults": 0,
          "wins": 1
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 86,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 42,
          "draws": 81,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.4",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 4,
          "model": "gpt-5.4",
          "point_rating_method": "sequential_elo",
          "public_id": "E-98ddce22d3eb5886",
          "rated_matches": 86,
          "raw_elo_rating": 1461.7295454760624,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 19.06652602077495,
          "uncertainty": 9.855626741889738,
          "unilateral_faults": 0,
          "wins": 1
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 86,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 42,
          "draws": 84,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.4-mini",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 2,
          "model": "gpt-5.4-mini",
          "point_rating_method": "sequential_elo",
          "public_id": "E-322cbb8be1559087",
          "rated_matches": 86,
          "raw_elo_rating": 1463.998408715422,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 19.57568162564367,
          "uncertainty": 9.855626741889738,
          "unilateral_faults": 0,
          "wins": 0
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 88,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 44,
          "draws": 81,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.4-nano",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-09T17:30:50Z",
          "losses": 7,
          "model": "gpt-5.4-nano",
          "point_rating_method": "sequential_elo",
          "public_id": "E-038a95fb13c8aa94",
          "rated_matches": 88,
          "raw_elo_rating": 1459.5120314275132,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "repaired",
          "score": 18.67763967670251,
          "uncertainty": 9.249894000318006,
          "unilateral_faults": 0,
          "wins": 0
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 86,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 43,
          "draws": 75,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.4-nano",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 7,
          "model": "gpt-5.4-nano",
          "point_rating_method": "sequential_elo",
          "public_id": "E-be95cc83ce87847c",
          "rated_matches": 86,
          "raw_elo_rating": 1463.5204302042953,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "repaired",
          "score": 19.4684184668401,
          "uncertainty": 9.855626741889738,
          "unilateral_faults": 0,
          "wins": 4
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 86,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 43,
          "draws": 77,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 9,
          "model": "gpt-5.5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-51e935956fa76015",
          "rated_matches": 86,
          "raw_elo_rating": 1475.225904404823,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 22.09524395964808,
          "uncertainty": 9.855626741889738,
          "unilateral_faults": 0,
          "wins": 0
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 64,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 31,
          "draws": 58,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.6-luna",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 6,
          "model": "gpt-5.6-luna",
          "point_rating_method": "sequential_elo",
          "public_id": "E-18fbed3cbf75c274",
          "rated_matches": 64,
          "raw_elo_rating": 1446.6966388554522,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 14.182848437029604,
          "uncertainty": 18.26736729460423,
          "unilateral_faults": 0,
          "wins": 0
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 86,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 43,
          "draws": 84,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.6-luna",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-10T05:30:29Z",
          "losses": 2,
          "model": "gpt-5.6-luna",
          "point_rating_method": "sequential_elo",
          "public_id": "E-ba4589e1cf2c827b",
          "rated_matches": 86,
          "raw_elo_rating": 1466.444458797462,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 20.124599730294026,
          "uncertainty": 9.855626741889738,
          "unilateral_faults": 0,
          "wins": 0
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 74,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 37,
          "draws": 59,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.6-sol",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-10T05:30:29Z",
          "losses": 9,
          "model": "gpt-5.6-sol",
          "point_rating_method": "sequential_elo",
          "public_id": "E-0420ca9039edc6fb",
          "rated_matches": 74,
          "raw_elo_rating": 1496.8193553515018,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 26.199687374521076,
          "uncertainty": 13.985026918962571,
          "unilateral_faults": 0,
          "wins": 6
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 70,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 30,
          "draws": 59,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.6-sol",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 5,
          "model": "gpt-5.6-sol",
          "point_rating_method": "sequential_elo",
          "public_id": "E-7b3b7d80a8f97b36",
          "rated_matches": 70,
          "raw_elo_rating": 1500.5055646014496,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 26.738936634036737,
          "uncertainty": 15.58908290969266,
          "unilateral_faults": 0,
          "wins": 6
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 104,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 52,
          "draws": 91,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.6-terra",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-10T05:30:29Z",
          "losses": 9,
          "model": "gpt-5.6-terra",
          "point_rating_method": "sequential_elo",
          "public_id": "E-c6593bd789768bdb",
          "rated_matches": 104,
          "raw_elo_rating": 1499.4681276807262,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "repaired",
          "score": 28.399082893812732,
          "uncertainty": 5.045003647426665,
          "unilateral_faults": 0,
          "wins": 4
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 118,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 47,
          "draws": 110,
          "evaluated_setting_identity": {
            "canonical_provider_route": "unknown_legacy",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "inclusionai/ling-3.0-flash:free",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 7,
          "model": "inclusionai/ling-3.0-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-fc495094a55d2f94",
          "rated_matches": 118,
          "raw_elo_rating": 1445.7308308182332,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 16.871313010451086,
          "uncertainty": 2.084924851410568,
          "unilateral_faults": 0,
          "wins": 1
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 100,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 50,
          "draws": 94,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "meituan/longcat-2.0",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 5,
          "model": "meituan/longcat-2.0",
          "point_rating_method": "sequential_elo",
          "public_id": "E-a0c74818516a7f27",
          "rated_matches": 100,
          "raw_elo_rating": 1457.7390320719044,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "none",
          "repair_status": "repaired",
          "score": 18.862874029135362,
          "uncertainty": 6.001859510499461,
          "unilateral_faults": 0,
          "wins": 1
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 68,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 31,
          "draws": 57,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "minimal",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "meta/muse-spark-1.2",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-08-13T16:58:34Z",
          "losses": 8,
          "model": "meta/muse-spark-1.2",
          "point_rating_method": "sequential_elo",
          "public_id": "E-0a492b508106c7e8",
          "rated_matches": 68,
          "raw_elo_rating": 1455.6017691862596,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "minimal",
          "repair_status": "first_pass",
          "score": 16.50878695816217,
          "uncertainty": 16.4429265428846,
          "unilateral_faults": 0,
          "wins": 3
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 72,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 35,
          "draws": 69,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "minimax/minimax-m3",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 3,
          "model": "minimax/minimax-m3",
          "point_rating_method": "sequential_elo",
          "public_id": "E-1e46941293882535",
          "rated_matches": 72,
          "raw_elo_rating": 1455.210402384003,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 16.721194515766282,
          "uncertainty": 14.770573598065289,
          "unilateral_faults": 0,
          "wins": 0
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 154,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 57,
          "draws": 136,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "low",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "moonshotai/kimi-k3",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T14:00:00Z",
          "losses": 10,
          "model": "moonshotai/kimi-k3",
          "point_rating_method": "sequential_elo",
          "public_id": "E-d3d3da42e99695b1",
          "rated_matches": 154,
          "raw_elo_rating": 1468.0575574041725,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "low",
          "repair_status": "first_pass",
          "score": 22.900288191407675,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 8
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 84,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 41,
          "draws": 71,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "nex-agi/nex-n2-pro",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-11T17:22:09Z",
          "losses": 11,
          "model": "nex-agi/nex-n2-pro",
          "point_rating_method": "sequential_elo",
          "public_id": "E-811f47e902ce0d21",
          "rated_matches": 84,
          "raw_elo_rating": 1451.0500885064464,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "none",
          "repair_status": "repaired",
          "score": 16.55738720588751,
          "uncertainty": 10.482614454664043,
          "unilateral_faults": 0,
          "wins": 2
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 106,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 52,
          "draws": 99,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "poolside/laguna-s-2.1",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 4,
          "model": "poolside/laguna-s-2.1",
          "point_rating_method": "sequential_elo",
          "public_id": "E-d8c7a78cc7f666dc",
          "rated_matches": 106,
          "raw_elo_rating": 1457.0890590046167,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "none",
          "repair_status": "repaired",
          "score": 18.971051988167996,
          "uncertainty": 4.586824452283178,
          "unilateral_faults": 0,
          "wins": 3
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 80,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 40,
          "draws": 66,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "qwen/qwen3.7-max",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 6,
          "model": "qwen/qwen3.7-max",
          "point_rating_method": "sequential_elo",
          "public_id": "E-5f64c2ae9860ba38",
          "rated_matches": 80,
          "raw_elo_rating": 1485.2151308299296,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 23.986859461426256,
          "uncertainty": 11.805555555555554,
          "unilateral_faults": 0,
          "wins": 8
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 92,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 45,
          "draws": 91,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "qwen/qwen3.7-plus",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 1,
          "model": "qwen/qwen3.7-plus",
          "point_rating_method": "sequential_elo",
          "public_id": "E-010dafcd7561851a",
          "rated_matches": 92,
          "raw_elo_rating": 1453.658322014426,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "none",
          "repair_status": "repaired",
          "score": 17.570880513249598,
          "uncertainty": 8.09758473652126,
          "unilateral_faults": 0,
          "wins": 0
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 17,
          "capped_draws": 0,
          "coverage_status": "under_covered",
          "distinct_rated_opponents": 8,
          "draws": 14,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "minimal",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "qwen/qwen3.8-max",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 3,
          "model": "qwen/qwen3.8-max",
          "point_rating_method": "sequential_elo",
          "public_id": "E-20f9463bfdcb2c8a",
          "rated_matches": 17,
          "raw_elo_rating": 1461.545523222252,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "minimal",
          "repair_status": "first_pass",
          "score": 7.491362721335916,
          "uncertainty": 74.10113019775793,
          "unilateral_faults": 0,
          "wins": 0
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 14,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 7,
          "draws": 9,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "low",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "stealth/ox-alpha",
            "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-08-22T00:27:26Z",
          "losses": 5,
          "model": "stealth/ox-alpha",
          "point_rating_method": "sequential_elo",
          "public_id": "E-06f983f13f9519d4",
          "rated_matches": 14,
          "raw_elo_rating": 1441.0405304647181,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "low",
          "repair_status": "first_pass",
          "score": 0.8704497902647038,
          "uncertainty": 85.34944487358055,
          "unilateral_faults": 0,
          "wins": 0
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 14,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 7,
          "draws": 10,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "low",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "stealth/ox-alpha",
            "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-08-22T00:27:26Z",
          "losses": 4,
          "model": "stealth/ox-alpha",
          "point_rating_method": "sequential_elo",
          "public_id": "E-aac195c51848d687",
          "rated_matches": 14,
          "raw_elo_rating": 1458.6853240806147,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "low",
          "repair_status": "first_pass",
          "score": 4.830117967012544,
          "uncertainty": 85.34944487358055,
          "unilateral_faults": 0,
          "wins": 0
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 14,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 7,
          "draws": 9,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "low",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "stealth/ox-alpha",
            "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-08-22T00:27:26Z",
          "losses": 4,
          "model": "stealth/ox-alpha",
          "point_rating_method": "sequential_elo",
          "public_id": "E-b633c9cf2d63b092",
          "rated_matches": 14,
          "raw_elo_rating": 1463.5225876446907,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "low",
          "repair_status": "first_pass",
          "score": 5.915648294777751,
          "uncertainty": 85.34944487358055,
          "unilateral_faults": 0,
          "wins": 1
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 72,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 36,
          "draws": 66,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "tencent/hy3-preview",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 6,
          "model": "tencent/hy3-preview",
          "point_rating_method": "sequential_elo",
          "public_id": "E-d910e47dd13c2c71",
          "rated_matches": 72,
          "raw_elo_rating": 1444.8163020312015,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "repaired",
          "score": 14.388654431203785,
          "uncertainty": 14.770573598065289,
          "unilateral_faults": 0,
          "wins": 0
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 102,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 50,
          "draws": 90,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "thinkingmachines/inkling",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 10,
          "model": "thinkingmachines/inkling",
          "point_rating_method": "sequential_elo",
          "public_id": "E-66a4f0abd099d8f1",
          "rated_matches": 102,
          "raw_elo_rating": 1484.3681592549508,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "repaired",
          "score": 24.925858625367727,
          "uncertainty": 5.516463908214657,
          "unilateral_faults": 0,
          "wins": 2
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 18,
          "capped_draws": 0,
          "coverage_status": "under_covered",
          "distinct_rated_opponents": 9,
          "draws": 18,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "thinkingmachines/inkling-small",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 0,
          "model": "thinkingmachines/inkling-small",
          "point_rating_method": "sequential_elo",
          "public_id": "E-161b7f406eb4d549",
          "rated_matches": 18,
          "raw_elo_rating": 1492.6020204364095,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 15.025055106927441,
          "uncertainty": 70.95786693528086,
          "unilateral_faults": 0,
          "wins": 0
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 127,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 50,
          "draws": 113,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "low",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "x-ai/grok-4.5",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T14:00:00Z",
          "losses": 9,
          "model": "x-ai/grok-4.5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-88ab68f664bd3ea0",
          "rated_matches": 127,
          "raw_elo_rating": 1491.590095915884,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "low",
          "repair_status": "first_pass",
          "score": 27.457151552126646,
          "uncertainty": 0.444173824159213,
          "unilateral_faults": 0,
          "wins": 5
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 66,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 33,
          "draws": 65,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "xiaomi/mimo-v2.5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-01T00:15:48Z",
          "losses": 1,
          "model": "xiaomi/mimo-v2.5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-39b08fe4c0318552",
          "rated_matches": 66,
          "raw_elo_rating": 1469.8584606204145,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 19.548028827872443,
          "uncertainty": 17.33472217815261,
          "unilateral_faults": 0,
          "wins": 0
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 78,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 39,
          "draws": 66,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "xiaomi/mimo-v2.5-pro",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 7,
          "model": "xiaomi/mimo-v2.5-pro",
          "point_rating_method": "sequential_elo",
          "public_id": "E-b9f44937a1269e8d",
          "rated_matches": 78,
          "raw_elo_rating": 1491.2790874838233,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 25.222210730949445,
          "uncertainty": 12.5043950463012,
          "unilateral_faults": 0,
          "wins": 5
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 66,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 33,
          "draws": 60,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "z-ai/glm-5.2",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 6,
          "model": "z-ai/glm-5.2",
          "point_rating_method": "sequential_elo",
          "public_id": "E-4959351a96fd2b82",
          "rated_matches": 66,
          "raw_elo_rating": 1435.4886349173833,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "repaired",
          "score": 11.835096161204495,
          "uncertainty": 17.33472217815261,
          "unilateral_faults": 0,
          "wins": 0
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 62,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 31,
          "draws": 58,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "z-ai/glm-5.2",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-11T14:00:45Z",
          "losses": 3,
          "model": "z-ai/glm-5.2",
          "point_rating_method": "sequential_elo",
          "public_id": "E-925b589068dc7268",
          "rated_matches": 62,
          "raw_elo_rating": 1474.219113041954,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "repaired",
          "score": 20.183819862570907,
          "uncertainty": 19.244078834871203,
          "unilateral_faults": 0,
          "wins": 1
        }
      ],
      "GB2-03": [
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 90,
          "capped_draws": 15,
          "coverage_status": "rated",
          "distinct_rated_opponents": 45,
          "draws": 62,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-opus-4-5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "omitted",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 15,
          "model": "claude-opus-4-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-1975db22db58e9b0",
          "rated_matches": 90,
          "raw_elo_rating": 1517.64293491248,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "omitted",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 48.527410514780094,
          "uncertainty": 8.664241836095918,
          "unilateral_faults": 0,
          "wins": 13
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 86,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 43,
          "draws": 11,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-opus-5",
            "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-25T15:48:00Z",
          "losses": 32,
          "model": "claude-opus-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-49aaba66f6b19080",
          "rated_matches": 86,
          "raw_elo_rating": 1627.3893994335508,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 63.34833623672766,
          "uncertainty": 9.855626741889738,
          "unilateral_faults": 0,
          "wins": 43
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 90,
          "capped_draws": 1,
          "coverage_status": "rated",
          "distinct_rated_opponents": 45,
          "draws": 24,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-opus-5",
            "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-25T15:48:00Z",
          "losses": 24,
          "model": "claude-opus-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-ecf847457e616425",
          "rated_matches": 90,
          "raw_elo_rating": 1495.7274710121853,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 45.54186550734778,
          "uncertainty": 8.664241836095918,
          "unilateral_faults": 0,
          "wins": 42
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 88,
          "capped_draws": 5,
          "coverage_status": "rated",
          "distinct_rated_opponents": 42,
          "draws": 31,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-sonnet-5",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 17,
          "model": "claude-sonnet-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-0d68a6f35cd9e672",
          "rated_matches": 88,
          "raw_elo_rating": 1613.9042805271881,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 61.57727285827689,
          "uncertainty": 9.249894000318006,
          "unilateral_faults": 0,
          "wins": 40
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 84,
          "capped_draws": 12,
          "coverage_status": "rated",
          "distinct_rated_opponents": 42,
          "draws": 36,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-sonnet-5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 27,
          "model": "claude-sonnet-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-e7d1e6857fc48e7a",
          "rated_matches": 84,
          "raw_elo_rating": 1506.3942752497016,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 46.796831298958985,
          "uncertainty": 10.482614454664043,
          "unilateral_faults": 0,
          "wins": 21
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 88,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 44,
          "draws": 40,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "deepseek/deepseek-v4-flash",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 28,
          "model": "deepseek/deepseek-v4-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-ae9d59ec3a8a1d63",
          "rated_matches": 88,
          "raw_elo_rating": 1430.6399776232663,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "repaired",
          "score": 36.61116549844097,
          "uncertainty": 9.249894000318006,
          "unilateral_faults": 0,
          "wins": 20
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 64,
          "capped_draws": 1,
          "coverage_status": "rated",
          "distinct_rated_opponents": 30,
          "draws": 18,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "deepseek/deepseek-v4-pro",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 29,
          "model": "deepseek/deepseek-v4-pro",
          "point_rating_method": "sequential_elo",
          "public_id": "E-f82a334a0fd1fb8e",
          "rated_matches": 64,
          "raw_elo_rating": 1410.1567925431275,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "repaired",
          "score": 32.83797916630326,
          "uncertainty": 18.26736729460423,
          "unilateral_faults": 0,
          "wins": 17
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 176,
          "capped_draws": 12,
          "coverage_status": "rated",
          "distinct_rated_opponents": 68,
          "draws": 52,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "minimal",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "google/gemini-3.5-flash-lite",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 51,
          "model": "google/gemini-3.5-flash-lite",
          "point_rating_method": "sequential_elo",
          "public_id": "E-28274045fbc35ae9",
          "rated_matches": 176,
          "raw_elo_rating": 1532.6867109455625,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "minimal",
          "repair_status": "repaired",
          "score": 52.19326999050381,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 73
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 163,
          "capped_draws": 4,
          "coverage_status": "rated",
          "distinct_rated_opponents": 65,
          "draws": 41,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "minimal",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "google/gemini-3.6-flash",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 44,
          "model": "google/gemini-3.6-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-6743f1c221046d65",
          "rated_matches": 163,
          "raw_elo_rating": 1539.217433989878,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "minimal",
          "repair_status": "first_pass",
          "score": 52.92370994301519,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 78
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 161,
          "capped_draws": 6,
          "coverage_status": "rated",
          "distinct_rated_opponents": 64,
          "draws": 66,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "minimal",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "google/gemini-3.6-flash",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 46,
          "model": "google/gemini-3.6-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-80b8c1a18d6dd238",
          "rated_matches": 161,
          "raw_elo_rating": 1504.4377526502255,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "minimal",
          "repair_status": "first_pass",
          "score": 48.15948624199781,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 49
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 84,
          "capped_draws": 2,
          "coverage_status": "rated",
          "distinct_rated_opponents": 42,
          "draws": 28,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-4.1",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "omitted",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 31,
          "model": "gpt-4.1",
          "point_rating_method": "sequential_elo",
          "public_id": "E-c7da9914f86ee846",
          "rated_matches": 84,
          "raw_elo_rating": 1521.331600253054,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "omitted",
          "reasoning_setting": "none",
          "repair_status": "repaired",
          "score": 48.831744011327004,
          "uncertainty": 10.482614454664043,
          "unilateral_faults": 0,
          "wins": 25
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 0,
          "capped_draws": 0,
          "coverage_status": "pending",
          "distinct_rated_opponents": 0,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "low",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5",
            "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-21T14:20:15Z",
          "losses": 0,
          "model": "gpt-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-c541923774f0cd7b",
          "rated_matches": 0,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "low",
          "repair_status": "repaired",
          "unilateral_faults": 0,
          "wins": 0
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 96,
          "capped_draws": 5,
          "coverage_status": "rated",
          "distinct_rated_opponents": 42,
          "draws": 52,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.4",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 34,
          "model": "gpt-5.4",
          "point_rating_method": "sequential_elo",
          "public_id": "E-ca34006c666b7c30",
          "rated_matches": 96,
          "raw_elo_rating": 1371.9311932402272,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 28.856580393425084,
          "uncertainty": 7.017308256680951,
          "unilateral_faults": 0,
          "wins": 10
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 82,
          "capped_draws": 4,
          "coverage_status": "rated",
          "distinct_rated_opponents": 41,
          "draws": 32,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.4",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 17,
          "model": "gpt-5.4",
          "point_rating_method": "sequential_elo",
          "public_id": "E-ebd456dc6b320c61",
          "rated_matches": 82,
          "raw_elo_rating": 1604.3956609608717,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 60.07677932346456,
          "uncertainty": 11.132129994845172,
          "unilateral_faults": 0,
          "wins": 33
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 84,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 42,
          "draws": 79,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.4-mini",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 4,
          "model": "gpt-5.4-mini",
          "point_rating_method": "sequential_elo",
          "public_id": "E-35117a2e624d7970",
          "rated_matches": 84,
          "raw_elo_rating": 1474.8658260094098,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 42.50170870197985,
          "uncertainty": 10.482614454664043,
          "unilateral_faults": 0,
          "wins": 1
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 90,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 45,
          "draws": 34,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.4-nano",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-09T17:30:50Z",
          "losses": 28,
          "model": "gpt-5.4-nano",
          "point_rating_method": "sequential_elo",
          "public_id": "E-f2a7b43bf689e68e",
          "rated_matches": 90,
          "raw_elo_rating": 1503.4667049734755,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 46.59618183026941,
          "uncertainty": 8.664241836095918,
          "unilateral_faults": 0,
          "wins": 28
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 82,
          "capped_draws": 7,
          "coverage_status": "rated",
          "distinct_rated_opponents": 41,
          "draws": 36,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 28,
          "model": "gpt-5.5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-446036823932df16",
          "rated_matches": 82,
          "raw_elo_rating": 1437.1973645808223,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 37.29934502959449,
          "uncertainty": 11.132129994845172,
          "unilateral_faults": 0,
          "wins": 18
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 94,
          "capped_draws": 4,
          "coverage_status": "rated",
          "distinct_rated_opponents": 42,
          "draws": 51,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.6-luna",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 40,
          "model": "gpt-5.6-luna",
          "point_rating_method": "sequential_elo",
          "public_id": "E-47dd28046ef904f9",
          "rated_matches": 94,
          "raw_elo_rating": 1347.201035529736,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 25.42965253398741,
          "uncertainty": 7.54891760425771,
          "unilateral_faults": 0,
          "wins": 3
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 78,
          "capped_draws": 1,
          "coverage_status": "rated",
          "distinct_rated_opponents": 38,
          "draws": 38,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.6-luna",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-10T05:30:29Z",
          "losses": 19,
          "model": "gpt-5.6-luna",
          "point_rating_method": "sequential_elo",
          "public_id": "E-d192bb239087b778",
          "rated_matches": 78,
          "raw_elo_rating": 1467.7893639049173,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 41.31733999385539,
          "uncertainty": 12.5043950463012,
          "unilateral_faults": 0,
          "wins": 21
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 82,
          "capped_draws": 15,
          "coverage_status": "rated",
          "distinct_rated_opponents": 41,
          "draws": 42,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.6-sol",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-10T05:30:29Z",
          "losses": 25,
          "model": "gpt-5.6-sol",
          "point_rating_method": "sequential_elo",
          "public_id": "E-527999604d620080",
          "rated_matches": 82,
          "raw_elo_rating": 1444.8744235238303,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 38.34519124591633,
          "uncertainty": 11.132129994845172,
          "unilateral_faults": 0,
          "wins": 15
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 92,
          "capped_draws": 7,
          "coverage_status": "rated",
          "distinct_rated_opponents": 43,
          "draws": 35,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.6-sol",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 19,
          "model": "gpt-5.6-sol",
          "point_rating_method": "sequential_elo",
          "public_id": "E-79655cafc06e8943",
          "rated_matches": 92,
          "raw_elo_rating": 1546.3926522758095,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 52.50574288116246,
          "uncertainty": 8.09758473652126,
          "unilateral_faults": 0,
          "wins": 38
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 80,
          "capped_draws": 9,
          "coverage_status": "rated",
          "distinct_rated_opponents": 40,
          "draws": 36,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.6-terra",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-10T10:07:13Z",
          "losses": 24,
          "model": "gpt-5.6-terra",
          "point_rating_method": "sequential_elo",
          "public_id": "E-c2f0f8f062659e83",
          "rated_matches": 80,
          "raw_elo_rating": 1515.2761169916803,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 47.862625672133966,
          "uncertainty": 11.805555555555554,
          "unilateral_faults": 0,
          "wins": 20
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 102,
          "capped_draws": 2,
          "coverage_status": "rated",
          "distinct_rated_opponents": 40,
          "draws": 40,
          "evaluated_setting_identity": {
            "canonical_provider_route": "unknown_legacy",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "inclusionai/ling-3.0-flash:free",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 47,
          "model": "inclusionai/ling-3.0-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-2524de3c7d4a81b7",
          "rated_matches": 102,
          "raw_elo_rating": 1305.971312261028,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "none",
          "repair_status": "repaired",
          "score": 20.034429808491304,
          "uncertainty": 5.516463908214657,
          "unilateral_faults": 0,
          "wins": 15
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 98,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 39,
          "draws": 47,
          "evaluated_setting_identity": {
            "canonical_provider_route": "unknown_legacy",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "inclusionai/ling-3.0-flash:free",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 30,
          "model": "inclusionai/ling-3.0-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-641ddca04b054d56",
          "rated_matches": 98,
          "raw_elo_rating": 1417.3184613791018,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "none",
          "repair_status": "repaired",
          "score": 35.09586303490573,
          "uncertainty": 6.501890762960602,
          "unilateral_faults": 0,
          "wins": 21
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 80,
          "capped_draws": 5,
          "coverage_status": "rated",
          "distinct_rated_opponents": 38,
          "draws": 35,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "meituan/longcat-2.0",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 33,
          "model": "meituan/longcat-2.0",
          "point_rating_method": "sequential_elo",
          "public_id": "E-198e8ddfe9f7ce20",
          "rated_matches": 80,
          "raw_elo_rating": 1320.9190075493696,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "none",
          "repair_status": "repaired",
          "score": 21.38534458904165,
          "uncertainty": 11.805555555555554,
          "unilateral_faults": 0,
          "wins": 12
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 86,
          "capped_draws": 9,
          "coverage_status": "rated",
          "distinct_rated_opponents": 41,
          "draws": 39,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "meituan/longcat-2.0",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 21,
          "model": "meituan/longcat-2.0",
          "point_rating_method": "sequential_elo",
          "public_id": "E-84709c769628f9a2",
          "rated_matches": 86,
          "raw_elo_rating": 1440.8637202178857,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 37.93793137950897,
          "uncertainty": 9.855626741889738,
          "unilateral_faults": 0,
          "wins": 26
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 92,
          "capped_draws": 1,
          "coverage_status": "rated",
          "distinct_rated_opponents": 43,
          "draws": 12,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "minimal",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "meta/muse-spark-1.2",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-08-13T16:58:34Z",
          "losses": 36,
          "model": "meta/muse-spark-1.2",
          "point_rating_method": "sequential_elo",
          "public_id": "E-0ed752547c3943ba",
          "rated_matches": 92,
          "raw_elo_rating": 1549.3266540892673,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "minimal",
          "repair_status": "first_pass",
          "score": 52.90544213032362,
          "uncertainty": 8.09758473652126,
          "unilateral_faults": 0,
          "wins": 44
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 92,
          "capped_draws": 1,
          "coverage_status": "rated",
          "distinct_rated_opponents": 46,
          "draws": 34,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "minimax/minimax-m3",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 26,
          "model": "minimax/minimax-m3",
          "point_rating_method": "sequential_elo",
          "public_id": "E-44cc758f104a74ab",
          "rated_matches": 92,
          "raw_elo_rating": 1464.257046359489,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 41.31640418901639,
          "uncertainty": 8.09758473652126,
          "unilateral_faults": 0,
          "wins": 32
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 158,
          "capped_draws": 3,
          "coverage_status": "rated",
          "distinct_rated_opponents": 67,
          "draws": 40,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "low",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "moonshotai/kimi-k3",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T14:00:00Z",
          "losses": 40,
          "model": "moonshotai/kimi-k3",
          "point_rating_method": "sequential_elo",
          "public_id": "E-09859be1b47131a0",
          "rated_matches": 158,
          "raw_elo_rating": 1571.4990999527986,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "low",
          "repair_status": "first_pass",
          "score": 57.255056886144494,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 78
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 68,
          "capped_draws": 7,
          "coverage_status": "rated",
          "distinct_rated_opponents": 32,
          "draws": 43,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "nex-agi/nex-n2-pro",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 15,
          "model": "nex-agi/nex-n2-pro",
          "point_rating_method": "sequential_elo",
          "public_id": "E-a05d4cef5f788f16",
          "rated_matches": 68,
          "raw_elo_rating": 1447.1051582810692,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "none",
          "repair_status": "repaired",
          "score": 38.07029226565205,
          "uncertainty": 16.4429265428846,
          "unilateral_faults": 0,
          "wins": 10
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 50,
          "capped_draws": 6,
          "coverage_status": "rated",
          "distinct_rated_opponents": 25,
          "draws": 38,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "nvidia/nemotron-3-ultra-550b-a55b",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 9,
          "model": "nvidia/nemotron-3-ultra-550b-a55b",
          "point_rating_method": "sequential_elo",
          "public_id": "E-eb6e8a61f620acfd",
          "rated_matches": 50,
          "raw_elo_rating": 1393.790497688098,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "repaired",
          "score": 29.736891928612994,
          "uncertainty": 26.264004201400486,
          "unilateral_faults": 0,
          "wins": 3
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 152,
          "capped_draws": 7,
          "coverage_status": "rated",
          "distinct_rated_opponents": 62,
          "draws": 63,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "low",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "openai/gpt-oss-120b",
            "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-21T14:20:15Z",
          "losses": 78,
          "model": "openai/gpt-oss-120b",
          "point_rating_method": "sequential_elo",
          "public_id": "E-c90a449ff5e7b79a",
          "rated_matches": 152,
          "raw_elo_rating": 1273.1146500874393,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "low",
          "repair_status": "first_pass",
          "score": 16.522204329731178,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 11
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 163,
          "capped_draws": 3,
          "coverage_status": "rated",
          "distinct_rated_opponents": 68,
          "draws": 69,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "poolside/laguna-s-2.1",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 49,
          "model": "poolside/laguna-s-2.1",
          "point_rating_method": "sequential_elo",
          "public_id": "E-7acc466aeae25d41",
          "rated_matches": 163,
          "raw_elo_rating": 1468.9437116258425,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 43.35031638346527,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 45
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 88,
          "capped_draws": 5,
          "coverage_status": "rated",
          "distinct_rated_opponents": 44,
          "draws": 40,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "poolside/laguna-s-2.1",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 28,
          "model": "poolside/laguna-s-2.1",
          "point_rating_method": "sequential_elo",
          "public_id": "E-91efdb0c216f8504",
          "rated_matches": 88,
          "raw_elo_rating": 1429.8575467811165,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "none",
          "repair_status": "repaired",
          "score": 36.50457489624934,
          "uncertainty": 9.249894000318006,
          "unilateral_faults": 0,
          "wins": 20
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 68,
          "capped_draws": 6,
          "coverage_status": "rated",
          "distinct_rated_opponents": 32,
          "draws": 52,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "qwen/qwen3.7-max",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 10,
          "model": "qwen/qwen3.7-max",
          "point_rating_method": "sequential_elo",
          "public_id": "E-3325ebad2ef000c1",
          "rated_matches": 68,
          "raw_elo_rating": 1426.0472522295584,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 35.201572417188274,
          "uncertainty": 16.4429265428846,
          "unilateral_faults": 0,
          "wins": 6
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 15,
          "capped_draws": 2,
          "coverage_status": "under_covered",
          "distinct_rated_opponents": 9,
          "draws": 7,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "minimal",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "qwen/qwen3.8-max",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 7,
          "model": "qwen/qwen3.8-max",
          "point_rating_method": "sequential_elo",
          "public_id": "E-da44e2f9cd203f91",
          "rated_matches": 15,
          "raw_elo_rating": 1440.2371045770194,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "minimal",
          "repair_status": "first_pass",
          "score": 30.071719571532732,
          "uncertainty": 81.25,
          "unilateral_faults": 0,
          "wins": 1
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 0,
          "capped_draws": 0,
          "coverage_status": "pending",
          "distinct_rated_opponents": 0,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "low",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "stealth/ox-alpha",
            "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-08-21T20:50:14Z",
          "losses": 0,
          "model": "stealth/ox-alpha",
          "point_rating_method": "sequential_elo",
          "public_id": "E-213cbd917b9e3b75",
          "rated_matches": 0,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "low",
          "repair_status": "first_pass",
          "unilateral_faults": 0,
          "wins": 0
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 0,
          "capped_draws": 0,
          "coverage_status": "pending",
          "distinct_rated_opponents": 0,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "low",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "stealth/ox-alpha",
            "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-08-21T20:50:14Z",
          "losses": 0,
          "model": "stealth/ox-alpha",
          "point_rating_method": "sequential_elo",
          "public_id": "E-8ba70fb303bf5927",
          "rated_matches": 0,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "low",
          "repair_status": "repaired",
          "unilateral_faults": 0,
          "wins": 0
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 13,
          "capped_draws": 1,
          "coverage_status": "rated",
          "distinct_rated_opponents": 6,
          "draws": 5,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "low",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "stealth/ox-alpha",
            "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-08-22T00:27:26Z",
          "losses": 5,
          "model": "stealth/ox-alpha",
          "point_rating_method": "sequential_elo",
          "public_id": "E-91f209f8f1ca6da4",
          "rated_matches": 12,
          "raw_elo_rating": 1465.647565832718,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "low",
          "repair_status": "repaired",
          "score": 32.043026060224584,
          "uncertainty": 94.92504905630729,
          "unilateral_faults": 1,
          "wins": 2
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 0,
          "capped_draws": 0,
          "coverage_status": "pending",
          "distinct_rated_opponents": 0,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "low",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "stealth/ox-alpha",
            "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-08-21T22:22:23Z",
          "losses": 0,
          "model": "stealth/ox-alpha",
          "point_rating_method": "sequential_elo",
          "public_id": "E-9f1a927cfaf6d760",
          "rated_matches": 0,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "low",
          "repair_status": "repaired",
          "unilateral_faults": 0,
          "wins": 0
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 0,
          "capped_draws": 0,
          "coverage_status": "pending",
          "distinct_rated_opponents": 0,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "low",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "stealth/ox-alpha",
            "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-08-21T22:22:23Z",
          "losses": 0,
          "model": "stealth/ox-alpha",
          "point_rating_method": "sequential_elo",
          "public_id": "E-a03a524a03b22367",
          "rated_matches": 0,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "low",
          "repair_status": "first_pass",
          "unilateral_faults": 0,
          "wins": 0
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 0,
          "capped_draws": 0,
          "coverage_status": "pending",
          "distinct_rated_opponents": 0,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "low",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "stealth/ox-alpha",
            "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-08-21T20:50:14Z",
          "losses": 0,
          "model": "stealth/ox-alpha",
          "point_rating_method": "sequential_elo",
          "public_id": "E-a4422e1fd753be13",
          "rated_matches": 0,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "low",
          "repair_status": "first_pass",
          "unilateral_faults": 0,
          "wins": 0
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 15,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 6,
          "draws": 6,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "low",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "stealth/ox-alpha",
            "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-08-22T00:27:26Z",
          "losses": 5,
          "model": "stealth/ox-alpha",
          "point_rating_method": "sequential_elo",
          "public_id": "E-acf0cd8991a453ef",
          "rated_matches": 11,
          "raw_elo_rating": 1434.814076597161,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "low",
          "repair_status": "first_pass",
          "score": 27.225453738660264,
          "uncertainty": 100.0,
          "unilateral_faults": 0,
          "wins": 0
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 0,
          "capped_draws": 0,
          "coverage_status": "pending",
          "distinct_rated_opponents": 0,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "low",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "stealth/ox-alpha",
            "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-08-21T22:22:23Z",
          "losses": 0,
          "model": "stealth/ox-alpha",
          "point_rating_method": "sequential_elo",
          "public_id": "E-eb6d338f3b9c76c6",
          "rated_matches": 0,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "low",
          "repair_status": "first_pass",
          "unilateral_faults": 0,
          "wins": 0
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 88,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 43,
          "draws": 30,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "tencent/hy3-preview",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 28,
          "model": "tencent/hy3-preview",
          "point_rating_method": "sequential_elo",
          "public_id": "E-2346cd049910cc0a",
          "rated_matches": 88,
          "raw_elo_rating": 1444.882558264278,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 38.551433143204484,
          "uncertainty": 9.249894000318006,
          "unilateral_faults": 0,
          "wins": 30
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 80,
          "capped_draws": 6,
          "coverage_status": "rated",
          "distinct_rated_opponents": 38,
          "draws": 44,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "thinkingmachines/inkling",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 18,
          "model": "thinkingmachines/inkling",
          "point_rating_method": "sequential_elo",
          "public_id": "E-78048b7c08122f1c",
          "rated_matches": 80,
          "raw_elo_rating": 1424.341435088916,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "repaired",
          "score": 35.47458831219506,
          "uncertainty": 11.805555555555554,
          "unilateral_faults": 0,
          "wins": 18
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 88,
          "capped_draws": 10,
          "coverage_status": "rated",
          "distinct_rated_opponents": 44,
          "draws": 37,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "thinkingmachines/inkling",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 19,
          "model": "thinkingmachines/inkling",
          "point_rating_method": "sequential_elo",
          "public_id": "E-adf1f0bb193bd39b",
          "rated_matches": 88,
          "raw_elo_rating": 1603.6268172129808,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 60.17717339305919,
          "uncertainty": 9.249894000318006,
          "unilateral_faults": 0,
          "wins": 32
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 16,
          "capped_draws": 0,
          "coverage_status": "under_covered",
          "distinct_rated_opponents": 9,
          "draws": 6,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "thinkingmachines/inkling-small",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 4,
          "model": "thinkingmachines/inkling-small",
          "point_rating_method": "sequential_elo",
          "public_id": "E-7a0adb70b85361e4",
          "rated_matches": 16,
          "raw_elo_rating": 1518.121643907326,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 41.08868410464794,
          "uncertainty": 77.5178125181665,
          "unilateral_faults": 0,
          "wins": 6
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 162,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 64,
          "draws": 42,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "low",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "x-ai/grok-4.5",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T14:00:00Z",
          "losses": 111,
          "model": "x-ai/grok-4.5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-02f7e54245bd5c85",
          "rated_matches": 162,
          "raw_elo_rating": 1150.82535220259,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "low",
          "repair_status": "repaired",
          "score": 0.0,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 9
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 88,
          "capped_draws": 1,
          "coverage_status": "rated",
          "distinct_rated_opponents": 44,
          "draws": 41,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "xiaomi/mimo-v2.5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 26,
          "model": "xiaomi/mimo-v2.5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-b10e12eb6aef112e",
          "rated_matches": 88,
          "raw_elo_rating": 1494.2810908524089,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 45.280998303857686,
          "uncertainty": 9.249894000318006,
          "unilateral_faults": 0,
          "wins": 21
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 70,
          "capped_draws": 6,
          "coverage_status": "rated",
          "distinct_rated_opponents": 33,
          "draws": 41,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "xiaomi/mimo-v2.5-pro",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 15,
          "model": "xiaomi/mimo-v2.5-pro",
          "point_rating_method": "sequential_elo",
          "public_id": "E-b0948c64dddf57ad",
          "rated_matches": 70,
          "raw_elo_rating": 1448.8646223820033,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "none",
          "repair_status": "repaired",
          "score": 38.40303950625073,
          "uncertainty": 15.58908290969266,
          "unilateral_faults": 0,
          "wins": 14
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 56,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 28,
          "draws": 32,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "z-ai/glm-5.2",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 12,
          "model": "z-ai/glm-5.2",
          "point_rating_method": "sequential_elo",
          "public_id": "E-4cab1ccd88bbeb2e",
          "rated_matches": 56,
          "raw_elo_rating": 1484.1155184175784,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 42.45463981090707,
          "uncertainty": 22.47661785325219,
          "unilateral_faults": 0,
          "wins": 12
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 60,
          "capped_draws": 5,
          "coverage_status": "rated",
          "distinct_rated_opponents": 30,
          "draws": 27,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "z-ai/glm-5.2",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-11T14:00:45Z",
          "losses": 21,
          "model": "z-ai/glm-5.2",
          "point_rating_method": "sequential_elo",
          "public_id": "E-583be34ca1fb2631",
          "rated_matches": 60,
          "raw_elo_rating": 1507.6715230136501,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "repaired",
          "score": 45.90433194761855,
          "uncertainty": 20.268439966447993,
          "unilateral_faults": 0,
          "wins": 12
        }
      ],
      "GB2-04": [
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 78,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 39,
          "draws": 50,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-opus-4-5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "omitted",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 14,
          "model": "claude-opus-4-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-9a77e43e752532c8",
          "rated_matches": 78,
          "raw_elo_rating": 1552.6081087252508,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "omitted",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 50.534733628873596,
          "uncertainty": 12.5043950463012,
          "unilateral_faults": 0,
          "wins": 14
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 84,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 41,
          "draws": 60,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-opus-4-8",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "omitted",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 15,
          "model": "claude-opus-4-8",
          "point_rating_method": "sequential_elo",
          "public_id": "E-688a139ef8557587",
          "rated_matches": 84,
          "raw_elo_rating": 1480.1348689981835,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "omitted",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 39.727863503836645,
          "uncertainty": 10.482614454664043,
          "unilateral_faults": 0,
          "wins": 9
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 100,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 50,
          "draws": 56,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-opus-5",
            "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-25T15:48:00Z",
          "losses": 27,
          "model": "claude-opus-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-72e9307528761b35",
          "rated_matches": 100,
          "raw_elo_rating": 1497.2404246856831,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 42.88350947764402,
          "uncertainty": 6.001859510499461,
          "unilateral_faults": 0,
          "wins": 17
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 104,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 52,
          "draws": 28,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-opus-5",
            "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-25T15:48:00Z",
          "losses": 29,
          "model": "claude-opus-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-9e7782014171d35f",
          "rated_matches": 104,
          "raw_elo_rating": 1604.0690744486421,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 59.29367755050637,
          "uncertainty": 5.045003647426665,
          "unilateral_faults": 0,
          "wins": 47
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 86,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 43,
          "draws": 69,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-sonnet-5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 7,
          "model": "claude-sonnet-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-be938b7d5557f479",
          "rated_matches": 86,
          "raw_elo_rating": 1509.157122022894,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 44.23081556016269,
          "uncertainty": 9.855626741889738,
          "unilateral_faults": 0,
          "wins": 10
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 74,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 36,
          "draws": 44,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-sonnet-5",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 17,
          "model": "claude-sonnet-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-d4f6be4f3a2580ef",
          "rated_matches": 74,
          "raw_elo_rating": 1490.4637763376538,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 40.87587184385918,
          "uncertainty": 13.985026918962571,
          "unilateral_faults": 0,
          "wins": 13
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 74,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 37,
          "draws": 44,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "deepseek/deepseek-v4-flash",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 26,
          "model": "deepseek/deepseek-v4-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-81bc9a578754f220",
          "rated_matches": 74,
          "raw_elo_rating": 1363.997401760583,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 21.587325373198095,
          "uncertainty": 13.985026918962571,
          "unilateral_faults": 0,
          "wins": 4
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 0,
          "capped_draws": 0,
          "coverage_status": "pending",
          "distinct_rated_opponents": 0,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "low",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "google/gemini-3.5-flash",
            "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-21T14:20:15Z",
          "losses": 0,
          "model": "google/gemini-3.5-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-33e6ff93f425b731",
          "rated_matches": 0,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "low",
          "repair_status": "first_pass",
          "unilateral_faults": 0,
          "wins": 0
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 134,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 51,
          "draws": 86,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "minimal",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "google/gemini-3.5-flash-lite",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 20,
          "model": "google/gemini-3.5-flash-lite",
          "point_rating_method": "sequential_elo",
          "public_id": "E-6a79049fd9ab6f5d",
          "rated_matches": 128,
          "raw_elo_rating": 1505.2695567320197,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "minimal",
          "repair_status": "first_pass",
          "score": 44.807170228357926,
          "uncertainty": 0.27254531628119416,
          "unilateral_faults": 0,
          "wins": 22
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 130,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 50,
          "draws": 77,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "minimal",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "google/gemini-3.5-flash-lite",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 25,
          "model": "google/gemini-3.5-flash-lite",
          "point_rating_method": "sequential_elo",
          "public_id": "E-b05b0185d0e8dc2a",
          "rated_matches": 130,
          "raw_elo_rating": 1511.2144902230677,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "minimal",
          "repair_status": "repaired",
          "score": 45.75504750592985,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 28
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 141,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 52,
          "draws": 117,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "minimal",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "google/gemini-3.6-flash",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 14,
          "model": "google/gemini-3.6-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-0b528ba96380a3b5",
          "rated_matches": 141,
          "raw_elo_rating": 1464.6512667915415,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "minimal",
          "repair_status": "first_pass",
          "score": 38.86387825220917,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 10
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 139,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 54,
          "draws": 101,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "minimal",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "google/gemini-3.6-flash",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 26,
          "model": "google/gemini-3.6-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-846809faa1345207",
          "rated_matches": 139,
          "raw_elo_rating": 1477.3695914012185,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "minimal",
          "repair_status": "repaired",
          "score": 40.767227315959126,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 12
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 88,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 43,
          "draws": 69,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "google/gemma-4-31b-it",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 9,
          "model": "google/gemma-4-31b-it",
          "point_rating_method": "sequential_elo",
          "public_id": "E-ec0cf4b37c805eee",
          "rated_matches": 88,
          "raw_elo_rating": 1478.369156952384,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 39.60896936866197,
          "uncertainty": 9.249894000318006,
          "unilateral_faults": 0,
          "wins": 10
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 84,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 42,
          "draws": 66,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-4.1",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "omitted",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 14,
          "model": "gpt-4.1",
          "point_rating_method": "sequential_elo",
          "public_id": "E-ecb06954153be8d5",
          "rated_matches": 84,
          "raw_elo_rating": 1457.7387499700872,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "omitted",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 36.31202602070684,
          "uncertainty": 10.482614454664043,
          "unilateral_faults": 0,
          "wins": 4
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 83,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 37,
          "draws": 42,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.4",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 29,
          "model": "gpt-5.4",
          "point_rating_method": "sequential_elo",
          "public_id": "E-5cd71ee548acca75",
          "rated_matches": 83,
          "raw_elo_rating": 1417.712515509699,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 30.16798634189743,
          "uncertainty": 10.804472558998102,
          "unilateral_faults": 0,
          "wins": 12
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 90,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 44,
          "draws": 71,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.4",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 8,
          "model": "gpt-5.4",
          "point_rating_method": "sequential_elo",
          "public_id": "E-8d62bf1b340a70dc",
          "rated_matches": 90,
          "raw_elo_rating": 1483.8733493227608,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 40.51992276550704,
          "uncertainty": 8.664241836095918,
          "unilateral_faults": 0,
          "wins": 11
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 90,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 44,
          "draws": 58,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.4-mini",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 16,
          "model": "gpt-5.4-mini",
          "point_rating_method": "sequential_elo",
          "public_id": "E-0880cdf1a43cb90c",
          "rated_matches": 90,
          "raw_elo_rating": 1460.0297776195794,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 36.883321001904825,
          "uncertainty": 8.664241836095918,
          "unilateral_faults": 0,
          "wins": 16
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 96,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 47,
          "draws": 66,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 18,
          "model": "gpt-5.5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-ba1aa87056709e9a",
          "rated_matches": 96,
          "raw_elo_rating": 1487.1646241939861,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 41.222856430705775,
          "uncertainty": 7.017308256680951,
          "unilateral_faults": 0,
          "wins": 12
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 78,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 38,
          "draws": 52,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.6-luna",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 15,
          "model": "gpt-5.6-luna",
          "point_rating_method": "sequential_elo",
          "public_id": "E-2c7615f28028f790",
          "rated_matches": 78,
          "raw_elo_rating": 1460.346288772209,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 36.463037436242594,
          "uncertainty": 12.5043950463012,
          "unilateral_faults": 0,
          "wins": 11
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 88,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 43,
          "draws": 68,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.6-luna",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-10T05:30:29Z",
          "losses": 13,
          "model": "gpt-5.6-luna",
          "point_rating_method": "sequential_elo",
          "public_id": "E-71a01107bf3f9fc1",
          "rated_matches": 88,
          "raw_elo_rating": 1475.7905244904262,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 39.21567848608893,
          "uncertainty": 9.249894000318006,
          "unilateral_faults": 0,
          "wins": 7
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 82,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 37,
          "draws": 54,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.6-sol",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 15,
          "model": "gpt-5.6-sol",
          "point_rating_method": "sequential_elo",
          "public_id": "E-66db807b1be40f67",
          "rated_matches": 82,
          "raw_elo_rating": 1494.2951959311706,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 41.80833395633762,
          "uncertainty": 11.132129994845172,
          "unilateral_faults": 0,
          "wins": 13
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 82,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 41,
          "draws": 63,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.6-sol",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-10T10:07:13Z",
          "losses": 6,
          "model": "gpt-5.6-sol",
          "point_rating_method": "sequential_elo",
          "public_id": "E-f0b7195272d6417e",
          "rated_matches": 82,
          "raw_elo_rating": 1498.3796453332363,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 42.431290788636126,
          "uncertainty": 11.132129994845172,
          "unilateral_faults": 0,
          "wins": 13
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 90,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 45,
          "draws": 76,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.6-terra",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-10T05:30:29Z",
          "losses": 6,
          "model": "gpt-5.6-terra",
          "point_rating_method": "sequential_elo",
          "public_id": "E-50ee0aadbc66fe0e",
          "rated_matches": 90,
          "raw_elo_rating": 1521.160171149716,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 46.206877878735085,
          "uncertainty": 8.664241836095918,
          "unilateral_faults": 0,
          "wins": 8
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 116,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 45,
          "draws": 102,
          "evaluated_setting_identity": {
            "canonical_provider_route": "unknown_legacy",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "inclusionai/ling-3.0-flash:free",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 7,
          "model": "inclusionai/ling-3.0-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-f38039bb8cc277a1",
          "rated_matches": 116,
          "raw_elo_rating": 1476.192389292363,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 40.10360954415184,
          "uncertainty": 2.4750163521024238,
          "unilateral_faults": 0,
          "wins": 7
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 102,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 51,
          "draws": 56,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "meituan/longcat-2.0",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 24,
          "model": "meituan/longcat-2.0",
          "point_rating_method": "sequential_elo",
          "public_id": "E-9e1d4bf411e97fa6",
          "rated_matches": 102,
          "raw_elo_rating": 1584.2614626043232,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 56.21511165223179,
          "uncertainty": 5.516463908214657,
          "unilateral_faults": 0,
          "wins": 22
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 76,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 36,
          "draws": 54,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "minimal",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "meta/muse-spark-1.2",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-08-13T16:58:34Z",
          "losses": 9,
          "model": "meta/muse-spark-1.2",
          "point_rating_method": "sequential_elo",
          "public_id": "E-3f1d300b580e2822",
          "rated_matches": 76,
          "raw_elo_rating": 1482.7694515360909,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "minimal",
          "repair_status": "first_pass",
          "score": 39.7944295068769,
          "uncertainty": 13.230288229818967,
          "unilateral_faults": 0,
          "wins": 13
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 156,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 63,
          "draws": 81,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "low",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "moonshotai/kimi-k3",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T14:00:00Z",
          "losses": 31,
          "model": "moonshotai/kimi-k3",
          "point_rating_method": "sequential_elo",
          "public_id": "E-3c06949f23d4a77f",
          "rated_matches": 156,
          "raw_elo_rating": 1514.343293683398,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "low",
          "repair_status": "repaired",
          "score": 46.69357274580004,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 44
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 96,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 47,
          "draws": 83,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "nex-agi/nex-n2-pro",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-11T17:22:09Z",
          "losses": 8,
          "model": "nex-agi/nex-n2-pro",
          "point_rating_method": "sequential_elo",
          "public_id": "E-6f4b3b55e4ec7cf5",
          "rated_matches": 96,
          "raw_elo_rating": 1464.340110846728,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "none",
          "repair_status": "repaired",
          "score": 37.74168060162787,
          "uncertainty": 7.017308256680951,
          "unilateral_faults": 0,
          "wins": 5
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 62,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 31,
          "draws": 48,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "nvidia/nemotron-3-ultra-550b-a55b",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 7,
          "model": "nvidia/nemotron-3-ultra-550b-a55b",
          "point_rating_method": "sequential_elo",
          "public_id": "E-f36b99b3d76fbb35",
          "rated_matches": 62,
          "raw_elo_rating": 1498.4721260722356,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 41.455613711503254,
          "uncertainty": 19.244078834871203,
          "unilateral_faults": 0,
          "wins": 7
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 132,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 52,
          "draws": 52,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "low",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "openai/gpt-oss-120b",
            "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-21T14:20:15Z",
          "losses": 71,
          "model": "openai/gpt-oss-120b",
          "point_rating_method": "sequential_elo",
          "public_id": "E-f6de1ce39e48807c",
          "rated_matches": 132,
          "raw_elo_rating": 1210.9553390354572,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "low",
          "repair_status": "repaired",
          "score": 0.0,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 9
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 74,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 36,
          "draws": 61,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "qwen/qwen3.7-plus",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 8,
          "model": "qwen/qwen3.7-plus",
          "point_rating_method": "sequential_elo",
          "public_id": "E-84b9a07f75f324e2",
          "rated_matches": 74,
          "raw_elo_rating": 1469.91418843072,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 37.7416657545222,
          "uncertainty": 13.985026918962571,
          "unilateral_faults": 0,
          "wins": 5
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 22,
          "capped_draws": 0,
          "coverage_status": "under_covered",
          "distinct_rated_opponents": 11,
          "draws": 17,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "minimal",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "qwen/qwen3.8-max",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 4,
          "model": "qwen/qwen3.8-max",
          "point_rating_method": "sequential_elo",
          "public_id": "E-91e0eadd75202409",
          "rated_matches": 22,
          "raw_elo_rating": 1458.4779270736012,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "minimal",
          "repair_status": "first_pass",
          "score": 30.32099723181149,
          "uncertainty": 60.5072070285374,
          "unilateral_faults": 0,
          "wins": 1
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 16,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 8,
          "draws": 11,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "low",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "stealth/ox-alpha",
            "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-08-22T00:27:26Z",
          "losses": 5,
          "model": "stealth/ox-alpha",
          "point_rating_method": "sequential_elo",
          "public_id": "E-2aaa1a2095c3d9b6",
          "rated_matches": 16,
          "raw_elo_rating": 1445.1248130404315,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "low",
          "repair_status": "first_pass",
          "score": 26.208836620893216,
          "uncertainty": 77.5178125181665,
          "unilateral_faults": 0,
          "wins": 0
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 16,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 8,
          "draws": 8,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "low",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "stealth/ox-alpha",
            "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-08-22T00:27:26Z",
          "losses": 7,
          "model": "stealth/ox-alpha",
          "point_rating_method": "sequential_elo",
          "public_id": "E-92dc825a33843ff8",
          "rated_matches": 16,
          "raw_elo_rating": 1430.6077613290613,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "low",
          "repair_status": "repaired",
          "score": 23.994707944490706,
          "uncertainty": 77.5178125181665,
          "unilateral_faults": 0,
          "wins": 1
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 16,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 8,
          "draws": 10,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "low",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "stealth/ox-alpha",
            "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-08-22T00:27:26Z",
          "losses": 4,
          "model": "stealth/ox-alpha",
          "point_rating_method": "sequential_elo",
          "public_id": "E-ac806e30e1bd1958",
          "rated_matches": 16,
          "raw_elo_rating": 1473.4725162866634,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "low",
          "repair_status": "repaired",
          "score": 30.532404788558484,
          "uncertainty": 77.5178125181665,
          "unilateral_faults": 0,
          "wins": 2
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 72,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 36,
          "draws": 44,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "tencent/hy3-preview",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 13,
          "model": "tencent/hy3-preview",
          "point_rating_method": "sequential_elo",
          "public_id": "E-3fd10f7865cc280e",
          "rated_matches": 72,
          "raw_elo_rating": 1506.6569734340017,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "repaired",
          "score": 43.249796081077825,
          "uncertainty": 14.770573598065289,
          "unilateral_faults": 0,
          "wins": 15
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 86,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 42,
          "draws": 47,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "thinkingmachines/inkling",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 21,
          "model": "thinkingmachines/inkling",
          "point_rating_method": "sequential_elo",
          "public_id": "E-646ff33c7bab8b13",
          "rated_matches": 86,
          "raw_elo_rating": 1423.5390952609764,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 31.17242519002416,
          "uncertainty": 9.855626741889738,
          "unilateral_faults": 0,
          "wins": 18
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 92,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 45,
          "draws": 77,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "thinkingmachines/inkling",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 11,
          "model": "thinkingmachines/inkling",
          "point_rating_method": "sequential_elo",
          "public_id": "E-ddc16fa197bfc7c5",
          "rated_matches": 92,
          "raw_elo_rating": 1481.1560146919048,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 40.174617999626136,
          "uncertainty": 8.09758473652126,
          "unilateral_faults": 0,
          "wins": 4
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 15,
          "capped_draws": 0,
          "coverage_status": "under_covered",
          "distinct_rated_opponents": 8,
          "draws": 13,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "thinkingmachines/inkling-small",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 0,
          "model": "thinkingmachines/inkling-small",
          "point_rating_method": "sequential_elo",
          "public_id": "E-a50e6392704c24e8",
          "rated_matches": 15,
          "raw_elo_rating": 1525.0357629986581,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 37.941404265071526,
          "uncertainty": 81.25,
          "unilateral_faults": 0,
          "wins": 2
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 133,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 51,
          "draws": 96,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "low",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "x-ai/grok-4.5",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T14:00:00Z",
          "losses": 21,
          "model": "x-ai/grok-4.5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-5a4033db1131bf1d",
          "rated_matches": 133,
          "raw_elo_rating": 1428.310826299396,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "low",
          "repair_status": "first_pass",
          "score": 33.17065439419427,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 16
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 74,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 37,
          "draws": 52,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "xiaomi/mimo-v2.5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-01T00:15:48Z",
          "losses": 4,
          "model": "xiaomi/mimo-v2.5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-7ad356726cce2b22",
          "rated_matches": 74,
          "raw_elo_rating": 1501.3005279978574,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "repaired",
          "score": 42.52868421147764,
          "uncertainty": 13.985026918962571,
          "unilateral_faults": 0,
          "wins": 18
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 70,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 35,
          "draws": 61,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "xiaomi/mimo-v2.5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T06:10:40Z",
          "losses": 6,
          "model": "xiaomi/mimo-v2.5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-d58c55e107783a21",
          "rated_matches": 70,
          "raw_elo_rating": 1463.8559190485062,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "repaired",
          "score": 36.62194410677851,
          "uncertainty": 15.58908290969266,
          "unilateral_faults": 0,
          "wins": 3
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 72,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 36,
          "draws": 53,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "z-ai/glm-5.2",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 10,
          "model": "z-ai/glm-5.2",
          "point_rating_method": "sequential_elo",
          "public_id": "E-1d5f5ff0402ff944",
          "rated_matches": 72,
          "raw_elo_rating": 1529.1774962447755,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "repaired",
          "score": 46.684607525873936,
          "uncertainty": 14.770573598065289,
          "unilateral_faults": 0,
          "wins": 9
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 82,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 41,
          "draws": 47,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "z-ai/glm-5.2",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-11T14:00:45Z",
          "losses": 19,
          "model": "z-ai/glm-5.2",
          "point_rating_method": "sequential_elo",
          "public_id": "E-f776c26a98306f5d",
          "rated_matches": 82,
          "raw_elo_rating": 1479.068861513742,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 39.48602607038318,
          "uncertainty": 11.132129994845172,
          "unilateral_faults": 0,
          "wins": 16
        }
      ],
      "GB2-05": [
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 106,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 53,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-opus-4-5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "omitted",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 40,
          "model": "claude-opus-4-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-934b5bc34a7e20b9",
          "rated_matches": 106,
          "raw_elo_rating": 1584.2090805580165,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "omitted",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 54.787452361508244,
          "uncertainty": 4.586824452283178,
          "unilateral_faults": 0,
          "wins": 66
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 98,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 49,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-opus-4-8",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "omitted",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 55,
          "model": "claude-opus-4-8",
          "point_rating_method": "sequential_elo",
          "public_id": "E-233f9cae6335e53d",
          "rated_matches": 98,
          "raw_elo_rating": 1386.8051899721886,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "omitted",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 38.26782236702627,
          "uncertainty": 6.501890762960602,
          "unilateral_faults": 0,
          "wins": 43
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 120,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 60,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-opus-5",
            "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-25T10:50:00Z",
          "losses": 12,
          "model": "claude-opus-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-09963ffe0b0fa5fd",
          "rated_matches": 120,
          "raw_elo_rating": 1997.878157235796,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 89.32998553777773,
          "uncertainty": 1.7045454545454586,
          "unilateral_faults": 0,
          "wins": 108
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 118,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 59,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-opus-5",
            "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-25T10:50:00Z",
          "losses": 12,
          "model": "claude-opus-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-b53cb955b1d8baab",
          "rated_matches": 118,
          "raw_elo_rating": 1955.1194704180377,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 85.75403715058349,
          "uncertainty": 2.084924851410568,
          "unilateral_faults": 0,
          "wins": 106
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 92,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 45,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-sonnet-5",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 63,
          "model": "claude-sonnet-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-66c9ddb5d274adfe",
          "rated_matches": 92,
          "raw_elo_rating": 1357.2618578161205,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 35.70854059047516,
          "uncertainty": 8.09758473652126,
          "unilateral_faults": 0,
          "wins": 29
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 100,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 50,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-sonnet-5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 46,
          "model": "claude-sonnet-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-e619c51e7d5d70d2",
          "rated_matches": 100,
          "raw_elo_rating": 1411.5046512373144,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 40.35208234845052,
          "uncertainty": 6.001859510499461,
          "unilateral_faults": 0,
          "wins": 54
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 114,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 57,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "deepseek/deepseek-v4-flash",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 64,
          "model": "deepseek/deepseek-v4-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-0dca18c79b6ac9d7",
          "rated_matches": 114,
          "raw_elo_rating": 1404.752960189545,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 39.99912971379366,
          "uncertainty": 2.875240412015687,
          "unilateral_faults": 0,
          "wins": 50
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 98,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 49,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "deepseek/deepseek-v4-pro",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 50,
          "model": "deepseek/deepseek-v4-pro",
          "point_rating_method": "sequential_elo",
          "public_id": "E-da5f3b1a4e370e1a",
          "rated_matches": 98,
          "raw_elo_rating": 1393.141045545112,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "repaired",
          "score": 38.79395147095302,
          "uncertainty": 6.501890762960602,
          "unilateral_faults": 0,
          "wins": 48
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 78,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 39,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "google/gemini-3.1-flash-lite",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 59,
          "model": "google/gemini-3.1-flash-lite",
          "point_rating_method": "sequential_elo",
          "public_id": "E-d979b43c3aeea657",
          "rated_matches": 78,
          "raw_elo_rating": 1136.308456520139,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 17.067829071463514,
          "uncertainty": 12.5043950463012,
          "unilateral_faults": 0,
          "wins": 19
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 0,
          "capped_draws": 0,
          "coverage_status": "pending",
          "distinct_rated_opponents": 0,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "low",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "google/gemini-3.5-flash",
            "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-21T14:20:15Z",
          "losses": 0,
          "model": "google/gemini-3.5-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-a13c4c9fdf6b244d",
          "rated_matches": 0,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "low",
          "repair_status": "first_pass",
          "unilateral_faults": 0,
          "wins": 0
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 166,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 60,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "minimal",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "google/gemini-3.5-flash-lite",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 141,
          "model": "google/gemini-3.5-flash-lite",
          "point_rating_method": "sequential_elo",
          "public_id": "E-214f636367cbdac4",
          "rated_matches": 164,
          "raw_elo_rating": 1069.3768340544518,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "minimal",
          "repair_status": "repaired",
          "score": 12.661059892346074,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 23
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 160,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 58,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "minimal",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "google/gemini-3.5-flash-lite",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 136,
          "model": "google/gemini-3.5-flash-lite",
          "point_rating_method": "sequential_elo",
          "public_id": "E-a870d09d3e1a40d4",
          "rated_matches": 160,
          "raw_elo_rating": 988.2545815273319,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "minimal",
          "repair_status": "first_pass",
          "score": 5.8927470205869374,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 24
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 159,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 65,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "minimal",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "google/gemini-3.6-flash",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 73,
          "model": "google/gemini-3.6-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-9bef179ce22a6c93",
          "rated_matches": 159,
          "raw_elo_rating": 1578.2068383181902,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "minimal",
          "repair_status": "first_pass",
          "score": 54.874182662406035,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 86
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 182,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 68,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "minimal",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "google/gemini-3.6-flash",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 75,
          "model": "google/gemini-3.6-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-e23af86eb5787555",
          "rated_matches": 182,
          "raw_elo_rating": 1432.2294603476682,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "minimal",
          "repair_status": "first_pass",
          "score": 42.922786979189105,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 107
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 94,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 47,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "google/gemma-4-31b-it",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 67,
          "model": "google/gemma-4-31b-it",
          "point_rating_method": "sequential_elo",
          "public_id": "E-e8e17fbbdd12faa4",
          "rated_matches": 94,
          "raw_elo_rating": 1136.0733751755404,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 17.377509992236185,
          "uncertainty": 7.54891760425771,
          "unilateral_faults": 0,
          "wins": 27
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 94,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 47,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-4.1",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "omitted",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 66,
          "model": "gpt-4.1",
          "point_rating_method": "sequential_elo",
          "public_id": "E-1b9f1f7b70f02927",
          "rated_matches": 94,
          "raw_elo_rating": 1135.4295707705774,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "omitted",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 17.324048509285905,
          "uncertainty": 7.54891760425771,
          "unilateral_faults": 0,
          "wins": 28
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 0,
          "capped_draws": 0,
          "coverage_status": "pending",
          "distinct_rated_opponents": 0,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "low",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5",
            "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-21T14:20:15Z",
          "losses": 0,
          "model": "gpt-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-d03d2c6a69fc3e16",
          "rated_matches": 0,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "low",
          "repair_status": "repaired",
          "unilateral_faults": 0,
          "wins": 0
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 92,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 46,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.4",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 25,
          "model": "gpt-5.4",
          "point_rating_method": "sequential_elo",
          "public_id": "E-6d3546010ef68f50",
          "rated_matches": 92,
          "raw_elo_rating": 1797.5895875968265,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "repaired",
          "score": 72.27333144424207,
          "uncertainty": 8.09758473652126,
          "unilateral_faults": 0,
          "wins": 67
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 90,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 43,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.4",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 32,
          "model": "gpt-5.4",
          "point_rating_method": "sequential_elo",
          "public_id": "E-a09c0b14cae46193",
          "rated_matches": 90,
          "raw_elo_rating": 1567.0954010065689,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 53.09546252248944,
          "uncertainty": 8.664241836095918,
          "unilateral_faults": 0,
          "wins": 58
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 94,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 47,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.4-mini",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 66,
          "model": "gpt-5.4-mini",
          "point_rating_method": "sequential_elo",
          "public_id": "E-427bdffeacc6c394",
          "rated_matches": 94,
          "raw_elo_rating": 1258.1950094624974,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "repaired",
          "score": 27.518483895121314,
          "uncertainty": 7.54891760425771,
          "unilateral_faults": 0,
          "wins": 28
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 88,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 44,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.4-nano",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-09T17:30:50Z",
          "losses": 67,
          "model": "gpt-5.4-nano",
          "point_rating_method": "sequential_elo",
          "public_id": "E-3311575b341ee4a8",
          "rated_matches": 88,
          "raw_elo_rating": 1193.8351500708243,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "repaired",
          "score": 22.061045463600173,
          "uncertainty": 9.249894000318006,
          "unilateral_faults": 0,
          "wins": 21
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 90,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 45,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.4-nano",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 69,
          "model": "gpt-5.4-nano",
          "point_rating_method": "sequential_elo",
          "public_id": "E-6c37eeef15b82287",
          "rated_matches": 90,
          "raw_elo_rating": 1144.518195047545,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "repaired",
          "score": 18.004674206350256,
          "uncertainty": 8.664241836095918,
          "unilateral_faults": 0,
          "wins": 21
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 92,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 46,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 40,
          "model": "gpt-5.5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-6f42dbbf02274b56",
          "rated_matches": 92,
          "raw_elo_rating": 1551.1627362890197,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 51.810059046408426,
          "uncertainty": 8.09758473652126,
          "unilateral_faults": 0,
          "wins": 52
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 88,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 43,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.6-luna",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-10T05:30:29Z",
          "losses": 79,
          "model": "gpt-5.6-luna",
          "point_rating_method": "sequential_elo",
          "public_id": "E-59156a669808a24f",
          "rated_matches": 86,
          "raw_elo_rating": 997.5922414110602,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "repaired",
          "score": 5.724804936416754,
          "uncertainty": 9.855626741889738,
          "unilateral_faults": 2,
          "wins": 7
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 92,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 43,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.6-luna",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 59,
          "model": "gpt-5.6-luna",
          "point_rating_method": "sequential_elo",
          "public_id": "E-6879be00992f95f0",
          "rated_matches": 92,
          "raw_elo_rating": 1273.8587217985935,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 28.782748688729765,
          "uncertainty": 8.09758473652126,
          "unilateral_faults": 0,
          "wins": 33
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 98,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 49,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.6-sol",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-10T05:30:29Z",
          "losses": 39,
          "model": "gpt-5.6-sol",
          "point_rating_method": "sequential_elo",
          "public_id": "E-471e9297eea18ffd",
          "rated_matches": 98,
          "raw_elo_rating": 1665.4347956065355,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 61.405209741565095,
          "uncertainty": 6.501890762960602,
          "unilateral_faults": 0,
          "wins": 59
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 90,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 43,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.6-sol",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 36,
          "model": "gpt-5.6-sol",
          "point_rating_method": "sequential_elo",
          "public_id": "E-d29c6c5eb08da2d9",
          "rated_matches": 90,
          "raw_elo_rating": 1509.1321010535598,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 48.282193230929145,
          "uncertainty": 8.664241836095918,
          "unilateral_faults": 0,
          "wins": 54
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 92,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 46,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.6-terra",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-10T05:30:29Z",
          "losses": 38,
          "model": "gpt-5.6-terra",
          "point_rating_method": "sequential_elo",
          "public_id": "E-1f00b423eab1c19d",
          "rated_matches": 92,
          "raw_elo_rating": 1567.3066590038927,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 53.15064951506388,
          "uncertainty": 8.09758473652126,
          "unilateral_faults": 0,
          "wins": 54
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 94,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 46,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "meituan/longcat-2.0",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 71,
          "model": "meituan/longcat-2.0",
          "point_rating_method": "sequential_elo",
          "public_id": "E-067ab716d64e3e9a",
          "rated_matches": 92,
          "raw_elo_rating": 1093.8498238628247,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "none",
          "repair_status": "repaired",
          "score": 13.834819544870367,
          "uncertainty": 8.09758473652126,
          "unilateral_faults": 2,
          "wins": 21
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 88,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 43,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "meituan/longcat-2.0",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 59,
          "model": "meituan/longcat-2.0",
          "point_rating_method": "sequential_elo",
          "public_id": "E-8cc657b7db4428cb",
          "rated_matches": 86,
          "raw_elo_rating": 1113.7152262954376,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 15.36765131751343,
          "uncertainty": 9.855626741889738,
          "unilateral_faults": 2,
          "wins": 27
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 92,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 43,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "minimal",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "meta/muse-spark-1.2",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-08-13T16:58:34Z",
          "losses": 42,
          "model": "meta/muse-spark-1.2",
          "point_rating_method": "sequential_elo",
          "public_id": "E-1fbf9ab6a0c6d3ee",
          "rated_matches": 92,
          "raw_elo_rating": 1565.788333723547,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "minimal",
          "repair_status": "first_pass",
          "score": 53.02456786594432,
          "uncertainty": 8.09758473652126,
          "unilateral_faults": 0,
          "wins": 50
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 114,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 57,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "minimax/minimax-m3",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 58,
          "model": "minimax/minimax-m3",
          "point_rating_method": "sequential_elo",
          "public_id": "E-33797d7b77c7800c",
          "rated_matches": 114,
          "raw_elo_rating": 1467.3464738181478,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "none",
          "repair_status": "repaired",
          "score": 45.19689169842294,
          "uncertainty": 2.875240412015687,
          "unilateral_faults": 0,
          "wins": 56
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 98,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 49,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "mistralai/mistral-medium-3-5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 52,
          "model": "mistralai/mistral-medium-3-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-4a7d37b86196302f",
          "rated_matches": 98,
          "raw_elo_rating": 1351.468176625996,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 35.33343869093166,
          "uncertainty": 6.501890762960602,
          "unilateral_faults": 0,
          "wins": 46
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 185,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 77,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "low",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "moonshotai/kimi-k3",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T14:00:00Z",
          "losses": 65,
          "model": "moonshotai/kimi-k3",
          "point_rating_method": "sequential_elo",
          "public_id": "E-4419230379dcd41e",
          "rated_matches": 185,
          "raw_elo_rating": 1633.2331677471427,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "low",
          "repair_status": "first_pass",
          "score": 59.63400603920557,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 120
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 106,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 53,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "nex-agi/nex-n2-pro",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-11T17:22:09Z",
          "losses": 53,
          "model": "nex-agi/nex-n2-pro",
          "point_rating_method": "sequential_elo",
          "public_id": "E-962a9da8812a74d4",
          "rated_matches": 106,
          "raw_elo_rating": 1463.6103813613147,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "none",
          "repair_status": "repaired",
          "score": 44.77294290610812,
          "uncertainty": 4.586824452283178,
          "unilateral_faults": 0,
          "wins": 53
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 88,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 44,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "nvidia/nemotron-3-ultra-550b-a55b",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 33,
          "model": "nvidia/nemotron-3-ultra-550b-a55b",
          "point_rating_method": "sequential_elo",
          "public_id": "E-4477e0de2e04aad4",
          "rated_matches": 88,
          "raw_elo_rating": 1593.0579629263639,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 55.212486240190024,
          "uncertainty": 9.249894000318006,
          "unilateral_faults": 0,
          "wins": 55
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 189,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 71,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "low",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "openai/gpt-oss-120b",
            "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-21T14:20:15Z",
          "losses": 153,
          "model": "openai/gpt-oss-120b",
          "point_rating_method": "sequential_elo",
          "public_id": "E-172336d3fd38632a",
          "rated_matches": 189,
          "raw_elo_rating": 1087.1904502695809,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "low",
          "repair_status": "repaired",
          "score": 14.31642168470547,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 36
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 102,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 51,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "poolside/laguna-s-2.1",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 24,
          "model": "poolside/laguna-s-2.1",
          "point_rating_method": "sequential_elo",
          "public_id": "E-1ca53619662c7f6f",
          "rated_matches": 102,
          "raw_elo_rating": 1818.408828937755,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 74.17362902574152,
          "uncertainty": 5.516463908214657,
          "unilateral_faults": 0,
          "wins": 78
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 94,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 47,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "poolside/laguna-s-2.1",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 47,
          "model": "poolside/laguna-s-2.1",
          "point_rating_method": "sequential_elo",
          "public_id": "E-21623e96b2b104e9",
          "rated_matches": 94,
          "raw_elo_rating": 1353.7896159286227,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "none",
          "repair_status": "repaired",
          "score": 35.45665484320768,
          "uncertainty": 7.54891760425771,
          "unilateral_faults": 0,
          "wins": 47
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 106,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 53,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "qwen/qwen3.7-max",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 53,
          "model": "qwen/qwen3.7-max",
          "point_rating_method": "sequential_elo",
          "public_id": "E-c577c41440c17864",
          "rated_matches": 106,
          "raw_elo_rating": 1515.586736592979,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 49.08905663197634,
          "uncertainty": 4.586824452283178,
          "unilateral_faults": 0,
          "wins": 53
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 102,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 51,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "qwen/qwen3.7-plus",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 54,
          "model": "qwen/qwen3.7-plus",
          "point_rating_method": "sequential_elo",
          "public_id": "E-94daaf1196d89c6c",
          "rated_matches": 102,
          "raw_elo_rating": 1476.341736666781,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 45.76839619365652,
          "uncertainty": 5.516463908214657,
          "unilateral_faults": 0,
          "wins": 48
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 17,
          "capped_draws": 0,
          "coverage_status": "under_covered",
          "distinct_rated_opponents": 9,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "minimal",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "qwen/qwen3.8-max",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 0,
          "model": "qwen/qwen3.8-max",
          "point_rating_method": "sequential_elo",
          "public_id": "E-776235fa35035a89",
          "rated_matches": 17,
          "raw_elo_rating": 1725.7042357575813,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "minimal",
          "repair_status": "first_pass",
          "score": 61.919231042616644,
          "uncertainty": 74.10113019775793,
          "unilateral_faults": 0,
          "wins": 17
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 16,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 8,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "low",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "stealth/ox-alpha",
            "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-08-22T00:27:26Z",
          "losses": 9,
          "model": "stealth/ox-alpha",
          "point_rating_method": "sequential_elo",
          "public_id": "E-070bbd8b3ce0460a",
          "rated_matches": 16,
          "raw_elo_rating": 1460.5264281995208,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "low",
          "repair_status": "repaired",
          "score": 39.67190336042129,
          "uncertainty": 77.5178125181665,
          "unilateral_faults": 0,
          "wins": 7
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 16,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 8,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "low",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "stealth/ox-alpha",
            "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-08-22T00:27:26Z",
          "losses": 7,
          "model": "stealth/ox-alpha",
          "point_rating_method": "sequential_elo",
          "public_id": "E-575e460fdd8ace42",
          "rated_matches": 16,
          "raw_elo_rating": 1513.161649921587,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "low",
          "repair_status": "first_pass",
          "score": 44.042729323999595,
          "uncertainty": 77.5178125181665,
          "unilateral_faults": 0,
          "wins": 9
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 16,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 8,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "low",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "stealth/ox-alpha",
            "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-08-22T00:27:26Z",
          "losses": 7,
          "model": "stealth/ox-alpha",
          "point_rating_method": "sequential_elo",
          "public_id": "E-c69bc9b31ddf984b",
          "rated_matches": 16,
          "raw_elo_rating": 1531.7349961269342,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "low",
          "repair_status": "first_pass",
          "score": 45.585058987841904,
          "uncertainty": 77.5178125181665,
          "unilateral_faults": 0,
          "wins": 9
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 154,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 56,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "low",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "stepfun/step-3.7-flash",
            "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-21T14:20:15Z",
          "losses": 99,
          "model": "stepfun/step-3.7-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-50f22f1c15a8fd4a",
          "rated_matches": 150,
          "raw_elo_rating": 1299.4636047831602,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "low",
          "repair_status": "first_pass",
          "score": 31.650235307750318,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 51
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 104,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 52,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "tencent/hy3-preview",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 63,
          "model": "tencent/hy3-preview",
          "point_rating_method": "sequential_elo",
          "public_id": "E-1bb81f8a4ae78954",
          "rated_matches": 104,
          "raw_elo_rating": 1329.3883779909766,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 33.59671726886273,
          "uncertainty": 5.045003647426665,
          "unilateral_faults": 0,
          "wins": 41
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 104,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 52,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "thinkingmachines/inkling",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 69,
          "model": "thinkingmachines/inkling",
          "point_rating_method": "sequential_elo",
          "public_id": "E-0f05573125dedc2b",
          "rated_matches": 104,
          "raw_elo_rating": 1292.1576760716523,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "repaired",
          "score": 30.505081796127445,
          "uncertainty": 5.045003647426665,
          "unilateral_faults": 0,
          "wins": 35
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 110,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 55,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "thinkingmachines/inkling",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 73,
          "model": "thinkingmachines/inkling",
          "point_rating_method": "sequential_elo",
          "public_id": "E-f7a1d86c7e241f8d",
          "rated_matches": 110,
          "raw_elo_rating": 1305.539750894517,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 31.70515499101209,
          "uncertainty": 3.707899787624953,
          "unilateral_faults": 0,
          "wins": 37
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 18,
          "capped_draws": 0,
          "coverage_status": "under_covered",
          "distinct_rated_opponents": 7,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "thinkingmachines/inkling-small",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 17,
          "model": "thinkingmachines/inkling-small",
          "point_rating_method": "sequential_elo",
          "public_id": "E-7c80d62319ac1a53",
          "rated_matches": 18,
          "raw_elo_rating": 1275.2637241074317,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 24.72348845861986,
          "uncertainty": 70.95786693528086,
          "unilateral_faults": 0,
          "wins": 1
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 161,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 65,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "low",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "x-ai/grok-4.5",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T14:00:00Z",
          "losses": 85,
          "model": "x-ai/grok-4.5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-3c5879def34f7d38",
          "rated_matches": 161,
          "raw_elo_rating": 1474.9702034985373,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "low",
          "repair_status": "first_pass",
          "score": 46.31767802468079,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 76
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 86,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 43,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "xiaomi/mimo-v2.5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 34,
          "model": "xiaomi/mimo-v2.5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-09d406abc15f7c9a",
          "rated_matches": 86,
          "raw_elo_rating": 1643.2983032623679,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 59.344201371796736,
          "uncertainty": 9.855626741889738,
          "unilateral_faults": 0,
          "wins": 52
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 86,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 43,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "xiaomi/mimo-v2.5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-01T00:15:48Z",
          "losses": 54,
          "model": "xiaomi/mimo-v2.5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-9490f08c56c27d13",
          "rated_matches": 86,
          "raw_elo_rating": 1295.9502483176454,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "repaired",
          "score": 30.500437685049647,
          "uncertainty": 9.855626741889738,
          "unilateral_faults": 0,
          "wins": 32
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 84,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 42,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "xiaomi/mimo-v2.5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T06:10:40Z",
          "losses": 45,
          "model": "xiaomi/mimo-v2.5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-be8fc9653466bbe1",
          "rated_matches": 84,
          "raw_elo_rating": 1375.0951588392095,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 37.03097475144065,
          "uncertainty": 10.482614454664043,
          "unilateral_faults": 0,
          "wins": 39
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 98,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 49,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "xiaomi/mimo-v2.5-pro",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 46,
          "model": "xiaomi/mimo-v2.5-pro",
          "point_rating_method": "sequential_elo",
          "public_id": "E-af55f57b03605914",
          "rated_matches": 98,
          "raw_elo_rating": 1444.8486850159818,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 43.08775105458573,
          "uncertainty": 6.501890762960602,
          "unilateral_faults": 0,
          "wins": 52
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 84,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 42,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "z-ai/glm-5.2",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-11T14:00:45Z",
          "losses": 40,
          "model": "z-ai/glm-5.2",
          "point_rating_method": "sequential_elo",
          "public_id": "E-38e323f4ce233fa1",
          "rated_matches": 84,
          "raw_elo_rating": 1403.656288266575,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 39.40268939357571,
          "uncertainty": 10.482614454664043,
          "unilateral_faults": 0,
          "wins": 44
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 82,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 41,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "z-ai/glm-5.2",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 42,
          "model": "z-ai/glm-5.2",
          "point_rating_method": "sequential_elo",
          "public_id": "E-d8655d29a4806df8",
          "rated_matches": 82,
          "raw_elo_rating": 1632.583520626269,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "repaired",
          "score": 58.369645792657955,
          "uncertainty": 11.132129994845172,
          "unilateral_faults": 0,
          "wins": 40
        }
      ],
      "GB2-06": [
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 96,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 48,
          "draws": 5,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-opus-4-5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "omitted",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 44,
          "model": "claude-opus-4-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-40a259ca8a40b5b4",
          "rated_matches": 96,
          "raw_elo_rating": 1433.511289483019,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "omitted",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 43.871714707416494,
          "uncertainty": 7.017308256680951,
          "unilateral_faults": 0,
          "wins": 47
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 90,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 45,
          "draws": 9,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-opus-4-8",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "omitted",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 30,
          "model": "claude-opus-4-8",
          "point_rating_method": "sequential_elo",
          "public_id": "E-db414178442322d3",
          "rated_matches": 90,
          "raw_elo_rating": 1559.4794101376715,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "omitted",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 54.6517518521781,
          "uncertainty": 8.664241836095918,
          "unilateral_faults": 0,
          "wins": 51
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 104,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 52,
          "draws": 11,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-opus-5",
            "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-25T10:50:00Z",
          "losses": 5,
          "model": "claude-opus-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-ca8985adf5006428",
          "rated_matches": 104,
          "raw_elo_rating": 1978.901816863329,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 91.17466067700593,
          "uncertainty": 5.045003647426665,
          "unilateral_faults": 0,
          "wins": 88
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 86,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 43,
          "draws": 3,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-sonnet-5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 39,
          "model": "claude-sonnet-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-500304c7462c6005",
          "rated_matches": 86,
          "raw_elo_rating": 1575.5939478505748,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 55.96294337993718,
          "uncertainty": 9.855626741889738,
          "unilateral_faults": 0,
          "wins": 44
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 94,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 43,
          "draws": 4,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-sonnet-5",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 45,
          "model": "claude-sonnet-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-63360bf4842cdf18",
          "rated_matches": 94,
          "raw_elo_rating": 1493.6367483030979,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 49.03470790545843,
          "uncertainty": 7.54891760425771,
          "unilateral_faults": 0,
          "wins": 45
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 90,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 44,
          "draws": 1,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "deepseek/deepseek-v4-flash",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 70,
          "model": "deepseek/deepseek-v4-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-db0efb02339d9e80",
          "rated_matches": 90,
          "raw_elo_rating": 1123.1640710825773,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 16.918306920549412,
          "uncertainty": 8.664241836095918,
          "unilateral_faults": 0,
          "wins": 19
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 86,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 43,
          "draws": 8,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "deepseek/deepseek-v4-pro",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 24,
          "model": "deepseek/deepseek-v4-pro",
          "point_rating_method": "sequential_elo",
          "public_id": "E-945bebaa34963e03",
          "rated_matches": 86,
          "raw_elo_rating": 1670.4616001827212,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 64.1672924244156,
          "uncertainty": 9.855626741889738,
          "unilateral_faults": 0,
          "wins": 54
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 80,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 40,
          "draws": 1,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "google/gemini-3.1-flash-lite",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 36,
          "model": "google/gemini-3.1-flash-lite",
          "point_rating_method": "sequential_elo",
          "public_id": "E-dc1c0f46738d1091",
          "rated_matches": 80,
          "raw_elo_rating": 1381.2364236832755,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 39.0195992003968,
          "uncertainty": 11.805555555555554,
          "unilateral_faults": 0,
          "wins": 43
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 0,
          "capped_draws": 0,
          "coverage_status": "pending",
          "distinct_rated_opponents": 0,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "low",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "google/gemini-3.5-flash",
            "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-21T14:20:15Z",
          "losses": 0,
          "model": "google/gemini-3.5-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-8d5209853815321d",
          "rated_matches": 0,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "low",
          "repair_status": "first_pass",
          "unilateral_faults": 0,
          "wins": 0
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 150,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 55,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "minimal",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "google/gemini-3.5-flash-lite",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 66,
          "model": "google/gemini-3.5-flash-lite",
          "point_rating_method": "sequential_elo",
          "public_id": "E-3efea50fdbbd1829",
          "rated_matches": 150,
          "raw_elo_rating": 1576.4149483402527,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "minimal",
          "repair_status": "first_pass",
          "score": 56.92756101091148,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 84
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 152,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 58,
          "draws": 4,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "minimal",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "google/gemini-3.5-flash-lite",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 50,
          "model": "google/gemini-3.5-flash-lite",
          "point_rating_method": "sequential_elo",
          "public_id": "E-46f1468c28505bfe",
          "rated_matches": 152,
          "raw_elo_rating": 1664.3918949877018,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "minimal",
          "repair_status": "repaired",
          "score": 64.55444772946453,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 98
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 168,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 60,
          "draws": 33,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "minimal",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "google/gemini-3.6-flash",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 89,
          "model": "google/gemini-3.6-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-5455742d003ec402",
          "rated_matches": 168,
          "raw_elo_rating": 1366.054909970448,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "minimal",
          "repair_status": "repaired",
          "score": 38.8893312853542,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 46
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 161,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 58,
          "draws": 2,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "minimal",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "google/gemini-3.6-flash",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 123,
          "model": "google/gemini-3.6-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-bb2e288b40b1a588",
          "rated_matches": 161,
          "raw_elo_rating": 1143.9370062291084,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "minimal",
          "repair_status": "first_pass",
          "score": 19.62323717799623,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 36
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 102,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 49,
          "draws": 2,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "google/gemma-4-31b-it",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 59,
          "model": "google/gemma-4-31b-it",
          "point_rating_method": "sequential_elo",
          "public_id": "E-da266f7bbd330107",
          "rated_matches": 102,
          "raw_elo_rating": 1313.9232512674864,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 33.633332893697606,
          "uncertainty": 5.516463908214657,
          "unilateral_faults": 0,
          "wins": 41
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 92,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 46,
          "draws": 10,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-4.1",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "omitted",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 35,
          "model": "gpt-4.1",
          "point_rating_method": "sequential_elo",
          "public_id": "E-4dcd6d3653c67437",
          "rated_matches": 92,
          "raw_elo_rating": 1555.174459690298,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "omitted",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 54.318655446755876,
          "uncertainty": 8.09758473652126,
          "unilateral_faults": 0,
          "wins": 47
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 84,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 42,
          "draws": 9,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.4",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 22,
          "model": "gpt-5.4",
          "point_rating_method": "sequential_elo",
          "public_id": "E-00a57c19a4229948",
          "rated_matches": 84,
          "raw_elo_rating": 1716.938756792082,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 68.14335365615862,
          "uncertainty": 10.482614454664043,
          "unilateral_faults": 0,
          "wins": 53
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 96,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 43,
          "draws": 4,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.4",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 18,
          "model": "gpt-5.4",
          "point_rating_method": "sequential_elo",
          "public_id": "E-eb2b19ed78a802af",
          "rated_matches": 96,
          "raw_elo_rating": 1780.420554955911,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "repaired",
          "score": 73.87313912064397,
          "uncertainty": 7.017308256680951,
          "unilateral_faults": 0,
          "wins": 74
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 98,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 47,
          "draws": 6,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.4-mini",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 46,
          "model": "gpt-5.4-mini",
          "point_rating_method": "sequential_elo",
          "public_id": "E-144154b792c9e9a6",
          "rated_matches": 98,
          "raw_elo_rating": 1335.615860264783,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "repaired",
          "score": 35.44117680027425,
          "uncertainty": 6.501890762960602,
          "unilateral_faults": 0,
          "wins": 46
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 100,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 48,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.4-nano",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-09T17:30:50Z",
          "losses": 55,
          "model": "gpt-5.4-nano",
          "point_rating_method": "sequential_elo",
          "public_id": "E-a1fb59d78d39d217",
          "rated_matches": 100,
          "raw_elo_rating": 1355.8723491350454,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 37.22759446407967,
          "uncertainty": 6.001859510499461,
          "unilateral_faults": 0,
          "wins": 45
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 96,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 48,
          "draws": 1,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.4-nano",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 31,
          "model": "gpt-5.4-nano",
          "point_rating_method": "sequential_elo",
          "public_id": "E-d5866895bf388f66",
          "rated_matches": 96,
          "raw_elo_rating": 1646.602219075191,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 62.30025511722427,
          "uncertainty": 7.017308256680951,
          "unilateral_faults": 0,
          "wins": 64
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 90,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 44,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.6-luna",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-10T05:30:29Z",
          "losses": 81,
          "model": "gpt-5.6-luna",
          "point_rating_method": "sequential_elo",
          "public_id": "E-ae522f9c5c491f57",
          "rated_matches": 90,
          "raw_elo_rating": 978.4527453835951,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 4.4033748279235585,
          "uncertainty": 8.664241836095918,
          "unilateral_faults": 0,
          "wins": 9
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 92,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 44,
          "draws": 3,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.6-luna",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 74,
          "model": "gpt-5.6-luna",
          "point_rating_method": "sequential_elo",
          "public_id": "E-d7a21b3fb5bd3acb",
          "rated_matches": 92,
          "raw_elo_rating": 1192.954172313164,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 22.993102472928516,
          "uncertainty": 8.09758473652126,
          "unilateral_faults": 0,
          "wins": 15
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 93,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 43,
          "draws": 3,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.6-sol",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 28,
          "model": "gpt-5.6-sol",
          "point_rating_method": "sequential_elo",
          "public_id": "E-69b849005fbfc624",
          "rated_matches": 93,
          "raw_elo_rating": 1656.6269296223352,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 63.111604396432526,
          "uncertainty": 7.821062312939668,
          "unilateral_faults": 0,
          "wins": 62
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 100,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 49,
          "draws": 3,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.6-sol",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-10T05:30:29Z",
          "losses": 58,
          "model": "gpt-5.6-sol",
          "point_rating_method": "sequential_elo",
          "public_id": "E-992b9a5ebbb74c80",
          "rated_matches": 100,
          "raw_elo_rating": 1364.2292853844367,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 37.95031944195105,
          "uncertainty": 6.001859510499461,
          "unilateral_faults": 0,
          "wins": 39
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 102,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 50,
          "draws": 2,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.6-terra",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-10T05:30:29Z",
          "losses": 53,
          "model": "gpt-5.6-terra",
          "point_rating_method": "sequential_elo",
          "public_id": "E-22ffdca36d9bac9c",
          "rated_matches": 102,
          "raw_elo_rating": 1373.9806181391325,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 38.82721709336295,
          "uncertainty": 5.516463908214657,
          "unilateral_faults": 0,
          "wins": 47
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 130,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 51,
          "draws": 4,
          "evaluated_setting_identity": {
            "canonical_provider_route": "unknown_legacy",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "inclusionai/ling-3.0-flash:free",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 70,
          "model": "inclusionai/ling-3.0-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-6807fffacebac165",
          "rated_matches": 130,
          "raw_elo_rating": 1285.4838250666692,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 31.559976136514084,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 56
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 128,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 49,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "unknown_legacy",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "inclusionai/ling-3.0-flash:free",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 122,
          "model": "inclusionai/ling-3.0-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-9bde0475193e2c4a",
          "rated_matches": 128,
          "raw_elo_rating": 920.8227548067191,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "none",
          "repair_status": "repaired",
          "score": 0.0,
          "uncertainty": 0.27254531628119416,
          "unilateral_faults": 0,
          "wins": 6
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 118,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 57,
          "draws": 6,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "meituan/longcat-2.0",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 65,
          "model": "meituan/longcat-2.0",
          "point_rating_method": "sequential_elo",
          "public_id": "E-3e8b2d11481a50d7",
          "rated_matches": 118,
          "raw_elo_rating": 1375.1951763308493,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "none",
          "repair_status": "repaired",
          "score": 39.16966780112746,
          "uncertainty": 2.084924851410568,
          "unilateral_faults": 0,
          "wins": 47
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 98,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 49,
          "draws": 14,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "meituan/longcat-2.0",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 43,
          "model": "meituan/longcat-2.0",
          "point_rating_method": "sequential_elo",
          "public_id": "E-e3023ff7ecf82fc4",
          "rated_matches": 98,
          "raw_elo_rating": 1541.6697695437547,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "none",
          "repair_status": "repaired",
          "score": 53.26114126809031,
          "uncertainty": 6.501890762960602,
          "unilateral_faults": 0,
          "wins": 41
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 94,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 43,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "minimal",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "meta/muse-spark-1.2",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-08-13T16:58:34Z",
          "losses": 69,
          "model": "meta/muse-spark-1.2",
          "point_rating_method": "sequential_elo",
          "public_id": "E-f5d3d04141e68bd0",
          "rated_matches": 94,
          "raw_elo_rating": 1250.7317045501534,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "minimal",
          "repair_status": "repaired",
          "score": 28.027781786573513,
          "uncertainty": 7.54891760425771,
          "unilateral_faults": 0,
          "wins": 25
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 90,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 44,
          "draws": 8,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "mistralai/mistral-medium-3-5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 47,
          "model": "mistralai/mistral-medium-3-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-cf0bc4a1e7a8d72a",
          "rated_matches": 90,
          "raw_elo_rating": 1323.4952044044514,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "repaired",
          "score": 34.24335399238109,
          "uncertainty": 8.664241836095918,
          "unilateral_faults": 0,
          "wins": 35
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 184,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 68,
          "draws": 20,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "low",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "moonshotai/kimi-k3",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T14:00:00Z",
          "losses": 70,
          "model": "moonshotai/kimi-k3",
          "point_rating_method": "sequential_elo",
          "public_id": "E-95a5c0e17cd4b70a",
          "rated_matches": 184,
          "raw_elo_rating": 1623.3658987890403,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "low",
          "repair_status": "first_pass",
          "score": 61.25978450989219,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 94
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 92,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 45,
          "draws": 2,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "nex-agi/nex-n2-pro",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-11T17:22:09Z",
          "losses": 67,
          "model": "nex-agi/nex-n2-pro",
          "point_rating_method": "sequential_elo",
          "public_id": "E-973417dedd770061",
          "rated_matches": 92,
          "raw_elo_rating": 1204.3990254582595,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "none",
          "repair_status": "repaired",
          "score": 23.982876833913124,
          "uncertainty": 8.09758473652126,
          "unilateral_faults": 0,
          "wins": 23
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 80,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 40,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "nvidia/nemotron-3-ultra-550b-a55b",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 49,
          "model": "nvidia/nemotron-3-ultra-550b-a55b",
          "point_rating_method": "sequential_elo",
          "public_id": "E-6e76a1c11ba24bc6",
          "rated_matches": 80,
          "raw_elo_rating": 1244.3425660567527,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "repaired",
          "score": 27.180737771836384,
          "uncertainty": 11.805555555555554,
          "unilateral_faults": 0,
          "wins": 31
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 168,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 62,
          "draws": 26,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "low",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "o3",
            "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-21T14:20:15Z",
          "losses": 115,
          "model": "o3",
          "point_rating_method": "sequential_elo",
          "public_id": "E-9f2773793ec1d7e3",
          "rated_matches": 168,
          "raw_elo_rating": 1154.7845709020912,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "low",
          "repair_status": "first_pass",
          "score": 20.618239276105058,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 27
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 171,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 67,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "low",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "openai/gpt-oss-120b",
            "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-21T14:20:15Z",
          "losses": 121,
          "model": "openai/gpt-oss-120b",
          "point_rating_method": "sequential_elo",
          "public_id": "E-b75de88bfc62ab22",
          "rated_matches": 171,
          "raw_elo_rating": 1181.1910568908093,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "low",
          "repair_status": "first_pass",
          "score": 22.92523467244584,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 50
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 108,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 52,
          "draws": 4,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "poolside/laguna-s-2.1",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 58,
          "model": "poolside/laguna-s-2.1",
          "point_rating_method": "sequential_elo",
          "public_id": "E-a29031412bc33c39",
          "rated_matches": 108,
          "raw_elo_rating": 1210.0954507274137,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 24.749232472982165,
          "uncertainty": 4.1413142610575715,
          "unilateral_faults": 0,
          "wins": 46
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 98,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 47,
          "draws": 2,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "qwen/qwen3.7-max",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 63,
          "model": "qwen/qwen3.7-max",
          "point_rating_method": "sequential_elo",
          "public_id": "E-0c7e9f6c7d4cb892",
          "rated_matches": 98,
          "raw_elo_rating": 1225.4277449994963,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 25.9118827156635,
          "uncertainty": 6.501890762960602,
          "unilateral_faults": 0,
          "wins": 33
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 99,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 48,
          "draws": 2,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "qwen/qwen3.7-plus",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 71,
          "model": "qwen/qwen3.7-plus",
          "point_rating_method": "sequential_elo",
          "public_id": "E-2fb82a23fdec2792",
          "rated_matches": 99,
          "raw_elo_rating": 1234.4468531079099,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 26.709300896929104,
          "uncertainty": 6.25,
          "unilateral_faults": 0,
          "wins": 26
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 16,
          "capped_draws": 0,
          "coverage_status": "under_covered",
          "distinct_rated_opponents": 10,
          "draws": 2,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "minimal",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "qwen/qwen3.8-max",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 11,
          "model": "qwen/qwen3.8-max",
          "point_rating_method": "sequential_elo",
          "public_id": "E-5142494e6069cc88",
          "rated_matches": 16,
          "raw_elo_rating": 1320.8161587044958,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "minimal",
          "repair_status": "first_pass",
          "score": 29.24798627908666,
          "uncertainty": 77.5178125181665,
          "unilateral_faults": 0,
          "wins": 3
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 14,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 7,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "low",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "stealth/ox-alpha",
            "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-08-22T00:27:26Z",
          "losses": 5,
          "model": "stealth/ox-alpha",
          "point_rating_method": "sequential_elo",
          "public_id": "E-026a6a472034feda",
          "rated_matches": 14,
          "raw_elo_rating": 1543.1180286222932,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "low",
          "repair_status": "first_pass",
          "score": 47.9312711936831,
          "uncertainty": 85.34944487358055,
          "unilateral_faults": 0,
          "wins": 9
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 14,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 7,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "low",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "stealth/ox-alpha",
            "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-08-22T00:27:26Z",
          "losses": 6,
          "model": "stealth/ox-alpha",
          "point_rating_method": "sequential_elo",
          "public_id": "E-30880d6c82cf51b1",
          "rated_matches": 14,
          "raw_elo_rating": 1525.0947706738589,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "low",
          "repair_status": "first_pass",
          "score": 46.37258290012322,
          "uncertainty": 85.34944487358055,
          "unilateral_faults": 0,
          "wins": 8
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 14,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 7,
          "draws": 1,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "low",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "stealth/ox-alpha",
            "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-08-22T00:27:26Z",
          "losses": 11,
          "model": "stealth/ox-alpha",
          "point_rating_method": "sequential_elo",
          "public_id": "E-8f80a28afb47af72",
          "rated_matches": 14,
          "raw_elo_rating": 1395.2824942652571,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "low",
          "repair_status": "repaired",
          "score": 35.14615113194093,
          "uncertainty": 85.34944487358055,
          "unilateral_faults": 0,
          "wins": 2
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 164,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 60,
          "draws": 11,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "low",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "stepfun/step-3.7-flash",
            "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-21T14:20:15Z",
          "losses": 68,
          "model": "stepfun/step-3.7-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-ab4ccc8ca01bc627",
          "rated_matches": 164,
          "raw_elo_rating": 1505.431236228724,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "low",
          "repair_status": "first_pass",
          "score": 50.91082045936282,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 85
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 112,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 54,
          "draws": 1,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "thinkingmachines/inkling",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 58,
          "model": "thinkingmachines/inkling",
          "point_rating_method": "sequential_elo",
          "public_id": "E-02be9616e86c7055",
          "rated_matches": 112,
          "raw_elo_rating": 1315.7125886364151,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "repaired",
          "score": 33.94239152620984,
          "uncertainty": 3.286043419179858,
          "unilateral_faults": 0,
          "wins": 53
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 21,
          "capped_draws": 0,
          "coverage_status": "under_covered",
          "distinct_rated_opponents": 10,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "thinkingmachines/inkling-small",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-08-18T19:25:55Z",
          "losses": 15,
          "model": "thinkingmachines/inkling-small",
          "point_rating_method": "sequential_elo",
          "public_id": "E-4166320c34322333",
          "rated_matches": 21,
          "raw_elo_rating": 1368.9037533119765,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "repaired",
          "score": 34.421477251042134,
          "uncertainty": 62.850358177805205,
          "unilateral_faults": 0,
          "wins": 6
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 163,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 60,
          "draws": 18,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "low",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "x-ai/grok-4.5",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T14:00:00Z",
          "losses": 68,
          "model": "x-ai/grok-4.5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-8dbfeb56f012d9c6",
          "rated_matches": 163,
          "raw_elo_rating": 1506.1558845685156,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "low",
          "repair_status": "first_pass",
          "score": 50.965291500953946,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 77
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 100,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 48,
          "draws": 3,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "xiaomi/mimo-v2.5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 56,
          "model": "xiaomi/mimo-v2.5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-d572bc902e0e416b",
          "rated_matches": 100,
          "raw_elo_rating": 1318.8645561550443,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 34.02708466427257,
          "uncertainty": 6.001859510499461,
          "unilateral_faults": 0,
          "wins": 41
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 82,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 41,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "xiaomi/mimo-v2.5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T06:10:40Z",
          "losses": 48,
          "model": "xiaomi/mimo-v2.5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-d79ad8bc05d1b933",
          "rated_matches": 82,
          "raw_elo_rating": 1351.9395132779148,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "repaired",
          "score": 36.53253371067762,
          "uncertainty": 11.132129994845172,
          "unilateral_faults": 0,
          "wins": 34
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 86,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 43,
          "draws": 1,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "xiaomi/mimo-v2.5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-01T00:15:48Z",
          "losses": 32,
          "model": "xiaomi/mimo-v2.5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-ff7683792b6b3363",
          "rated_matches": 86,
          "raw_elo_rating": 1650.6471645214087,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 62.45369941048074,
          "uncertainty": 9.855626741889738,
          "unilateral_faults": 0,
          "wins": 53
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 102,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 51,
          "draws": 1,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "xiaomi/mimo-v2.5-pro",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 45,
          "model": "xiaomi/mimo-v2.5-pro",
          "point_rating_method": "sequential_elo",
          "public_id": "E-6b662c734cdcff91",
          "rated_matches": 102,
          "raw_elo_rating": 1421.6211054795062,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "none",
          "repair_status": "repaired",
          "score": 42.94726409759388,
          "uncertainty": 5.516463908214657,
          "unilateral_faults": 0,
          "wins": 56
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 78,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 39,
          "draws": 10,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "z-ai/glm-5.2",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-11T14:00:45Z",
          "losses": 32,
          "model": "z-ai/glm-5.2",
          "point_rating_method": "sequential_elo",
          "public_id": "E-657c61c9039ce566",
          "rated_matches": 78,
          "raw_elo_rating": 1500.231437603409,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 49.26218227671022,
          "uncertainty": 12.5043950463012,
          "unilateral_faults": 0,
          "wins": 36
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 72,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 36,
          "draws": 6,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "z-ai/glm-5.2",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 33,
          "model": "z-ai/glm-5.2",
          "point_rating_method": "sequential_elo",
          "public_id": "E-ec1479c855f477b4",
          "rated_matches": 72,
          "raw_elo_rating": 1698.8979955999437,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "repaired",
          "score": 66.28648644885837,
          "uncertainty": 14.770573598065289,
          "unilateral_faults": 0,
          "wins": 33
        }
      ],
      "GB2-07": [
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 110,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 55,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-opus-4-5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "omitted",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 53,
          "model": "claude-opus-4-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-ca22621c58b6f244",
          "rated_matches": 110,
          "raw_elo_rating": 1463.297529638152,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "omitted",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 43.356649989805135,
          "uncertainty": 3.707899787624953,
          "unilateral_faults": 0,
          "wins": 57
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 96,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 48,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-opus-4-8",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "omitted",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 39,
          "model": "claude-opus-4-8",
          "point_rating_method": "sequential_elo",
          "public_id": "E-76804598cce96e62",
          "rated_matches": 96,
          "raw_elo_rating": 1550.4563465439146,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "omitted",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 51.31003172352387,
          "uncertainty": 7.017308256680951,
          "unilateral_faults": 0,
          "wins": 57
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 100,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 50,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-opus-5",
            "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-25T10:50:00Z",
          "losses": 22,
          "model": "claude-opus-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-914b104a64ab3110",
          "rated_matches": 100,
          "raw_elo_rating": 1856.1879837603456,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 80.15897505759567,
          "uncertainty": 6.001859510499461,
          "unilateral_faults": 0,
          "wins": 78
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 88,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 42,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-sonnet-5",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 52,
          "model": "claude-sonnet-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-754e53d1d8048114",
          "rated_matches": 88,
          "raw_elo_rating": 1404.3673294676476,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 37.39346503245966,
          "uncertainty": 9.249894000318006,
          "unilateral_faults": 0,
          "wins": 36
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 96,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 48,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-sonnet-5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 44,
          "model": "claude-sonnet-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-cd6f193a087d8c8d",
          "rated_matches": 96,
          "raw_elo_rating": 1604.343784837266,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 56.38139398455826,
          "uncertainty": 7.017308256680951,
          "unilateral_faults": 0,
          "wins": 52
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 100,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 46,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "unknown_legacy",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "cohere/north-mini-code:free",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 51,
          "model": "cohere/north-mini-code",
          "point_rating_method": "sequential_elo",
          "public_id": "E-3b908f26a42804a4",
          "rated_matches": 100,
          "raw_elo_rating": 1433.728927617014,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 40.4012322141799,
          "uncertainty": 6.001859510499461,
          "unilateral_faults": 0,
          "wins": 49
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 94,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 43,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "unknown_legacy",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "cohere/north-mini-code:free",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-11T17:22:09Z",
          "losses": 79,
          "model": "cohere/north-mini-code",
          "point_rating_method": "sequential_elo",
          "public_id": "E-c7f5dc6d5d3c2a8d",
          "rated_matches": 90,
          "raw_elo_rating": 1101.4407853335463,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "none",
          "repair_status": "repaired",
          "score": 8.929053864680773,
          "uncertainty": 8.664241836095918,
          "unilateral_faults": 4,
          "wins": 11
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 84,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 42,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "deepseek/deepseek-v4-flash",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 48,
          "model": "deepseek/deepseek-v4-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-c394c0713cfcfaa4",
          "rated_matches": 84,
          "raw_elo_rating": 1337.0075281912582,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 30.9614054899469,
          "uncertainty": 10.482614454664043,
          "unilateral_faults": 0,
          "wins": 36
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 100,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 49,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "deepseek/deepseek-v4-pro",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 43,
          "model": "deepseek/deepseek-v4-pro",
          "point_rating_method": "sequential_elo",
          "public_id": "E-f76d96b0f3163d4b",
          "rated_matches": 100,
          "raw_elo_rating": 1445.5598229415996,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "repaired",
          "score": 41.51464116371525,
          "uncertainty": 6.001859510499461,
          "unilateral_faults": 0,
          "wins": 57
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 74,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 37,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "google/gemini-3.1-flash-lite",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 70,
          "model": "google/gemini-3.1-flash-lite",
          "point_rating_method": "sequential_elo",
          "public_id": "E-3d6a15fe821fe6ad",
          "rated_matches": 74,
          "raw_elo_rating": 1010.8187961005,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 0.0,
          "uncertainty": 13.985026918962571,
          "unilateral_faults": 0,
          "wins": 4
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 0,
          "capped_draws": 0,
          "coverage_status": "pending",
          "distinct_rated_opponents": 0,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "low",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "google/gemini-3.5-flash",
            "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-21T14:20:15Z",
          "losses": 0,
          "model": "google/gemini-3.5-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-c9fe3c158f1169e0",
          "rated_matches": 0,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "low",
          "repair_status": "first_pass",
          "unilateral_faults": 0,
          "wins": 0
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 146,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 57,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "minimal",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "google/gemini-3.5-flash-lite",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 68,
          "model": "google/gemini-3.5-flash-lite",
          "point_rating_method": "sequential_elo",
          "public_id": "E-455ee67905f5f955",
          "rated_matches": 146,
          "raw_elo_rating": 1628.2860708460423,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "minimal",
          "repair_status": "first_pass",
          "score": 59.351955880308026,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 78
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 152,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 60,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "minimal",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "google/gemini-3.5-flash-lite",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 29,
          "model": "google/gemini-3.5-flash-lite",
          "point_rating_method": "sequential_elo",
          "public_id": "E-e2e240babaf0b862",
          "rated_matches": 152,
          "raw_elo_rating": 1840.53891009651,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "minimal",
          "repair_status": "first_pass",
          "score": 79.38861936508546,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 123
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 163,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 56,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "minimal",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "google/gemini-3.6-flash",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 92,
          "model": "google/gemini-3.6-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-8e9b51be911dad38",
          "rated_matches": 159,
          "raw_elo_rating": 1401.9459636158317,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "minimal",
          "repair_status": "first_pass",
          "score": 38.179829200282775,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 67
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 152,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 60,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "minimal",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "google/gemini-3.6-flash",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 55,
          "model": "google/gemini-3.6-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-a2d90fcdc2f4ef9d",
          "rated_matches": 152,
          "raw_elo_rating": 1712.8186002917869,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "minimal",
          "repair_status": "first_pass",
          "score": 67.36882440683803,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 97
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 88,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 43,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "google/gemma-4-31b-it",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 59,
          "model": "google/gemma-4-31b-it",
          "point_rating_method": "sequential_elo",
          "public_id": "E-3f820f7e8ff15839",
          "rated_matches": 86,
          "raw_elo_rating": 1217.1234130773007,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "none",
          "repair_status": "repaired",
          "score": 19.726281854437815,
          "uncertainty": 9.855626741889738,
          "unilateral_faults": 2,
          "wins": 27
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 88,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 44,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-4.1",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "omitted",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 48,
          "model": "gpt-4.1",
          "point_rating_method": "sequential_elo",
          "public_id": "E-fcfa606d3cbb0ba0",
          "rated_matches": 88,
          "raw_elo_rating": 1530.801634444942,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "omitted",
          "reasoning_setting": "none",
          "repair_status": "repaired",
          "score": 49.29223370785008,
          "uncertainty": 9.249894000318006,
          "unilateral_faults": 0,
          "wins": 40
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 0,
          "capped_draws": 0,
          "coverage_status": "pending",
          "distinct_rated_opponents": 0,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "low",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5",
            "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-21T14:20:15Z",
          "losses": 0,
          "model": "gpt-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-a67f59519ca31035",
          "rated_matches": 0,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "low",
          "repair_status": "first_pass",
          "unilateral_faults": 0,
          "wins": 0
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 96,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 42,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.4",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 62,
          "model": "gpt-5.4",
          "point_rating_method": "sequential_elo",
          "public_id": "E-323834608cbfa7f4",
          "rated_matches": 96,
          "raw_elo_rating": 1371.1011530410074,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 34.43086306273809,
          "uncertainty": 7.017308256680951,
          "unilateral_faults": 0,
          "wins": 34
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 88,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 44,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.4",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 52,
          "model": "gpt-5.4",
          "point_rating_method": "sequential_elo",
          "public_id": "E-c8176c382cf75e88",
          "rated_matches": 88,
          "raw_elo_rating": 1234.169410217102,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 21.376090075886736,
          "uncertainty": 9.249894000318006,
          "unilateral_faults": 0,
          "wins": 36
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 90,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 44,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.4-mini",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 74,
          "model": "gpt-5.4-mini",
          "point_rating_method": "sequential_elo",
          "public_id": "E-c2ab31787514c10c",
          "rated_matches": 88,
          "raw_elo_rating": 1090.5750082161858,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 7.8623797518037435,
          "uncertainty": 9.249894000318006,
          "unilateral_faults": 2,
          "wins": 14
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 100,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 50,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.4-nano",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 62,
          "model": "gpt-5.4-nano",
          "point_rating_method": "sequential_elo",
          "public_id": "E-4e14ae758717169e",
          "rated_matches": 100,
          "raw_elo_rating": 1303.316043587365,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "repaired",
          "score": 28.128038323977535,
          "uncertainty": 6.001859510499461,
          "unilateral_faults": 0,
          "wins": 38
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 112,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 56,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 54,
          "model": "gpt-5.5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-4edfe4117ad3e936",
          "rated_matches": 112,
          "raw_elo_rating": 1464.820592135627,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 43.53174665691214,
          "uncertainty": 3.286043419179858,
          "unilateral_faults": 0,
          "wins": 58
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 92,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 42,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.6-luna",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 79,
          "model": "gpt-5.6-luna",
          "point_rating_method": "sequential_elo",
          "public_id": "E-8fd5624103eac132",
          "rated_matches": 92,
          "raw_elo_rating": 1147.5819193516577,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 13.314071820038254,
          "uncertainty": 8.09758473652126,
          "unilateral_faults": 0,
          "wins": 13
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 87,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 43,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.6-luna",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-10T05:30:29Z",
          "losses": 69,
          "model": "gpt-5.6-luna",
          "point_rating_method": "sequential_elo",
          "public_id": "E-ea529147555b5f2e",
          "rated_matches": 86,
          "raw_elo_rating": 1096.9350151518765,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 8.415317281672394,
          "uncertainty": 9.855626741889738,
          "unilateral_faults": 1,
          "wins": 17
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 92,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 46,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.6-sol",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-10T05:30:29Z",
          "losses": 40,
          "model": "gpt-5.6-sol",
          "point_rating_method": "sequential_elo",
          "public_id": "E-bef852aad169a609",
          "rated_matches": 92,
          "raw_elo_rating": 1643.747048162753,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 60.00831428515665,
          "uncertainty": 8.09758473652126,
          "unilateral_faults": 0,
          "wins": 52
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 93,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 43,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.6-sol",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 37,
          "model": "gpt-5.6-sol",
          "point_rating_method": "sequential_elo",
          "public_id": "E-e65ec062f67d1b0b",
          "rated_matches": 93,
          "raw_elo_rating": 1545.286379381379,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 50.76297141256903,
          "uncertainty": 7.821062312939668,
          "unilateral_faults": 0,
          "wins": 56
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 108,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 53,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.6-terra",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-10T05:30:29Z",
          "losses": 60,
          "model": "gpt-5.6-terra",
          "point_rating_method": "sequential_elo",
          "public_id": "E-8ebe8776c7d44d46",
          "rated_matches": 108,
          "raw_elo_rating": 1407.8298422557973,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 38.10393902588812,
          "uncertainty": 4.1413142610575715,
          "unilateral_faults": 0,
          "wins": 48
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 100,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 49,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "meituan/longcat-2.0",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 47,
          "model": "meituan/longcat-2.0",
          "point_rating_method": "sequential_elo",
          "public_id": "E-c1f595f47c71e648",
          "rated_matches": 100,
          "raw_elo_rating": 1378.491617776272,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 35.20283315496975,
          "uncertainty": 6.001859510499461,
          "unilateral_faults": 0,
          "wins": 53
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 108,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 53,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "meituan/longcat-2.0",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 56,
          "model": "meituan/longcat-2.0",
          "point_rating_method": "sequential_elo",
          "public_id": "E-e2db910734ca5315",
          "rated_matches": 108,
          "raw_elo_rating": 1475.8309211848266,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "none",
          "repair_status": "repaired",
          "score": 44.50354005188175,
          "uncertainty": 4.1413142610575715,
          "unilateral_faults": 0,
          "wins": 52
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 88,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 42,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "minimal",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "meta/muse-spark-1.2",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-08-13T16:58:34Z",
          "losses": 58,
          "model": "meta/muse-spark-1.2",
          "point_rating_method": "sequential_elo",
          "public_id": "E-5618329845b079c7",
          "rated_matches": 88,
          "raw_elo_rating": 1339.6829441858488,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "minimal",
          "repair_status": "first_pass",
          "score": 31.305998996116344,
          "uncertainty": 9.249894000318006,
          "unilateral_faults": 0,
          "wins": 30
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 88,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 44,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "minimax/minimax-m3",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 51,
          "model": "minimax/minimax-m3",
          "point_rating_method": "sequential_elo",
          "public_id": "E-24e15c4d7490cdf3",
          "rated_matches": 88,
          "raw_elo_rating": 1367.2693290956158,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "none",
          "repair_status": "repaired",
          "score": 33.90216158577543,
          "uncertainty": 9.249894000318006,
          "unilateral_faults": 0,
          "wins": 37
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 178,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 70,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "low",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "moonshotai/kimi-k3",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T14:00:00Z",
          "losses": 121,
          "model": "moonshotai/kimi-k3",
          "point_rating_method": "sequential_elo",
          "public_id": "E-4d8815930b656774",
          "rated_matches": 178,
          "raw_elo_rating": 1289.9508601455611,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "low",
          "repair_status": "first_pass",
          "score": 27.802313254046688,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 57
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 96,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 48,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "nex-agi/nex-n2-pro",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-11T17:22:09Z",
          "losses": 29,
          "model": "nex-agi/nex-n2-pro",
          "point_rating_method": "sequential_elo",
          "public_id": "E-1006c453b0c3a745",
          "rated_matches": 96,
          "raw_elo_rating": 1648.1717121399788,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "none",
          "repair_status": "repaired",
          "score": 60.50605278337446,
          "uncertainty": 7.017308256680951,
          "unilateral_faults": 0,
          "wins": 67
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 74,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 37,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "nvidia/nemotron-3-ultra-550b-a55b",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-03T18:15:00Z",
          "losses": 62,
          "model": "nvidia/nemotron-3-ultra-550b-a55b",
          "point_rating_method": "sequential_elo",
          "public_id": "E-0e1c7f89e1c19b69",
          "rated_matches": 74,
          "raw_elo_rating": 1144.8702182648058,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 12.615617756799654,
          "uncertainty": 13.985026918962571,
          "unilateral_faults": 0,
          "wins": 12
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 166,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 62,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "low",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "o3",
            "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-21T14:20:15Z",
          "losses": 80,
          "model": "o3",
          "point_rating_method": "sequential_elo",
          "public_id": "E-585aa996c86c4b8a",
          "rated_matches": 166,
          "raw_elo_rating": 1543.6832616568183,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "low",
          "repair_status": "first_pass",
          "score": 51.58180645988167,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 86
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 168,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 64,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "low",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "openai/gpt-oss-120b",
            "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-21T14:20:15Z",
          "losses": 142,
          "model": "openai/gpt-oss-120b",
          "point_rating_method": "sequential_elo",
          "public_id": "E-759d747bb732d949",
          "rated_matches": 168,
          "raw_elo_rating": 1108.1862556209687,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "low",
          "repair_status": "first_pass",
          "score": 10.614346337124728,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 26
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 109,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 49,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "poolside/laguna-s-2.1",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 63,
          "model": "poolside/laguna-s-2.1",
          "point_rating_method": "sequential_elo",
          "public_id": "E-069a963abdd14cdf",
          "rated_matches": 100,
          "raw_elo_rating": 1464.3369924640717,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 43.28176596870082,
          "uncertainty": 6.001859510499461,
          "unilateral_faults": 0,
          "wins": 37
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 102,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 51,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "poolside/laguna-s-2.1",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 50,
          "model": "poolside/laguna-s-2.1",
          "point_rating_method": "sequential_elo",
          "public_id": "E-d8e68d23876f6d21",
          "rated_matches": 102,
          "raw_elo_rating": 1623.6832947172982,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 58.31443671515227,
          "uncertainty": 5.516463908214657,
          "unilateral_faults": 0,
          "wins": 52
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 90,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 45,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "qwen/qwen3.7-max",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 32,
          "model": "qwen/qwen3.7-max",
          "point_rating_method": "sequential_elo",
          "public_id": "E-3142a09c7f192060",
          "rated_matches": 90,
          "raw_elo_rating": 1703.2609653449783,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 65.56652347725021,
          "uncertainty": 8.664241836095918,
          "unilateral_faults": 0,
          "wins": 58
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 86,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 42,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "qwen/qwen3.7-plus",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 66,
          "model": "qwen/qwen3.7-plus",
          "point_rating_method": "sequential_elo",
          "public_id": "E-737a66790985a5e6",
          "rated_matches": 84,
          "raw_elo_rating": 1053.14781558953,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 4.247286587507169,
          "uncertainty": 10.482614454664043,
          "unilateral_faults": 2,
          "wins": 18
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 19,
          "capped_draws": 0,
          "coverage_status": "under_covered",
          "distinct_rated_opponents": 10,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "minimal",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "qwen/qwen3.8-max",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 7,
          "model": "qwen/qwen3.8-max",
          "point_rating_method": "sequential_elo",
          "public_id": "E-9060604c6d76c81b",
          "rated_matches": 19,
          "raw_elo_rating": 1558.924963586655,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "minimal",
          "repair_status": "first_pass",
          "score": 47.51171651636437,
          "uncertainty": 68.05339887498948,
          "unilateral_faults": 0,
          "wins": 12
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 16,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 8,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "low",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "stealth/ox-alpha",
            "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-08-22T00:27:26Z",
          "losses": 4,
          "model": "stealth/ox-alpha",
          "point_rating_method": "sequential_elo",
          "public_id": "E-b7e03d205460428f",
          "rated_matches": 16,
          "raw_elo_rating": 1595.1872718968311,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "low",
          "repair_status": "first_pass",
          "score": 50.21181379936904,
          "uncertainty": 77.5178125181665,
          "unilateral_faults": 0,
          "wins": 12
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 16,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 8,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "low",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "stealth/ox-alpha",
            "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-08-22T00:27:26Z",
          "losses": 10,
          "model": "stealth/ox-alpha",
          "point_rating_method": "sequential_elo",
          "public_id": "E-c2beebe255c607a1",
          "rated_matches": 16,
          "raw_elo_rating": 1445.8719739585094,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "low",
          "repair_status": "first_pass",
          "score": 36.15970831910282,
          "uncertainty": 77.5178125181665,
          "unilateral_faults": 0,
          "wins": 6
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 16,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 8,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "low",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "stealth/ox-alpha",
            "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-08-22T00:27:26Z",
          "losses": 13,
          "model": "stealth/ox-alpha",
          "point_rating_method": "sequential_elo",
          "public_id": "E-f9e2fbd96bb7a98d",
          "rated_matches": 16,
          "raw_elo_rating": 1384.185625165754,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "low",
          "repair_status": "first_pass",
          "score": 30.354388355930954,
          "uncertainty": 77.5178125181665,
          "unilateral_faults": 0,
          "wins": 3
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 178,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 68,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "low",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "stepfun/step-3.7-flash",
            "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-21T14:20:15Z",
          "losses": 109,
          "model": "stepfun/step-3.7-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-1140a7c92290e8f4",
          "rated_matches": 178,
          "raw_elo_rating": 1378.7192000023038,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "low",
          "repair_status": "repaired",
          "score": 36.156327157500364,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 69
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 104,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 51,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "thinkingmachines/inkling",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 56,
          "model": "thinkingmachines/inkling",
          "point_rating_method": "sequential_elo",
          "public_id": "E-062d41f517db2ccb",
          "rated_matches": 104,
          "raw_elo_rating": 1320.0660988276552,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 29.776430806523866,
          "uncertainty": 5.045003647426665,
          "unilateral_faults": 0,
          "wins": 48
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 20,
          "capped_draws": 0,
          "coverage_status": "under_covered",
          "distinct_rated_opponents": 11,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "thinkingmachines/inkling-small",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 14,
          "model": "thinkingmachines/inkling-small",
          "point_rating_method": "sequential_elo",
          "public_id": "E-f330739aca81e515",
          "rated_matches": 20,
          "raw_elo_rating": 1405.8173258582663,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "repaired",
          "score": 33.305573503838346,
          "uncertainty": 65.3589451179962,
          "unilateral_faults": 0,
          "wins": 6
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 146,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 57,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "low",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "x-ai/grok-4.5",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T14:00:00Z",
          "losses": 33,
          "model": "x-ai/grok-4.5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-1d206565b78f3121",
          "rated_matches": 146,
          "raw_elo_rating": 1761.1992839087297,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "low",
          "repair_status": "first_pass",
          "score": 71.8604564523625,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 113
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 88,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 43,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "xiaomi/mimo-v2.5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 59,
          "model": "xiaomi/mimo-v2.5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-0984b025e9005f5b",
          "rated_matches": 86,
          "raw_elo_rating": 1137.1745265340696,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "none",
          "repair_status": "repaired",
          "score": 12.202269229827921,
          "uncertainty": 9.855626741889738,
          "unilateral_faults": 2,
          "wins": 27
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 88,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 44,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "xiaomi/mimo-v2.5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-01T00:15:48Z",
          "losses": 40,
          "model": "xiaomi/mimo-v2.5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-47d67dcf0077af42",
          "rated_matches": 88,
          "raw_elo_rating": 1496.523954140653,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 46.066351390998115,
          "uncertainty": 9.249894000318006,
          "unilateral_faults": 0,
          "wins": 48
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 94,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 47,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "xiaomi/mimo-v2.5-pro",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 37,
          "model": "xiaomi/mimo-v2.5-pro",
          "point_rating_method": "sequential_elo",
          "public_id": "E-83580d03385c6759",
          "rated_matches": 94,
          "raw_elo_rating": 1539.1060983283344,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 50.20183268472181,
          "uncertainty": 7.54891760425771,
          "unilateral_faults": 0,
          "wins": 57
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 74,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 37,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "z-ai/glm-5.2",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-11T14:00:45Z",
          "losses": 44,
          "model": "z-ai/glm-5.2",
          "point_rating_method": "sequential_elo",
          "public_id": "E-62e8714f035ebc68",
          "rated_matches": 74,
          "raw_elo_rating": 1404.082365452216,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 37.01014721451399,
          "uncertainty": 13.985026918962571,
          "unilateral_faults": 0,
          "wins": 30
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 78,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 39,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "z-ai/glm-5.2",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 39,
          "model": "z-ai/glm-5.2",
          "point_rating_method": "sequential_elo",
          "public_id": "E-e31f275ab7ef3741",
          "rated_matches": 78,
          "raw_elo_rating": 1634.8958569158183,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 58.843545195365074,
          "uncertainty": 12.5043950463012,
          "unilateral_faults": 0,
          "wins": 39
        }
      ],
      "GB2-08": [
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 90,
          "capped_draws": 6,
          "coverage_status": "rated",
          "distinct_rated_opponents": 45,
          "draws": 6,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-opus-4-5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "omitted",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 19,
          "model": "claude-opus-4-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-01b57d5e6655f927",
          "rated_matches": 90,
          "raw_elo_rating": 1770.4607839572238,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "omitted",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 69.43814796420975,
          "uncertainty": 8.664241836095918,
          "unilateral_faults": 0,
          "wins": 65
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 90,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 45,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-opus-4-8",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "omitted",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 25,
          "model": "claude-opus-4-8",
          "point_rating_method": "sequential_elo",
          "public_id": "E-c9d7578e8375d994",
          "rated_matches": 90,
          "raw_elo_rating": 1773.8635077665217,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "omitted",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 69.78217372191577,
          "uncertainty": 8.664241836095918,
          "unilateral_faults": 0,
          "wins": 65
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 162,
          "capped_draws": 16,
          "coverage_status": "rated",
          "distinct_rated_opponents": 62,
          "draws": 16,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-opus-5",
            "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-25T10:50:00Z",
          "losses": 20,
          "model": "claude-opus-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-43cc1c89fa5720b3",
          "rated_matches": 162,
          "raw_elo_rating": 1842.3354939772314,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 77.77669137324924,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 126
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 114,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 57,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-opus-5",
            "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-25T10:50:00Z",
          "losses": 37,
          "model": "claude-opus-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-5a7942274854aaa6",
          "rated_matches": 114,
          "raw_elo_rating": 1628.0363266293714,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 55.506829401848854,
          "uncertainty": 2.875240412015687,
          "unilateral_faults": 0,
          "wins": 77
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 86,
          "capped_draws": 34,
          "coverage_status": "rated",
          "distinct_rated_opponents": 42,
          "draws": 34,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-sonnet-5",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 27,
          "model": "claude-sonnet-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-c2e7d7e507756f84",
          "rated_matches": 86,
          "raw_elo_rating": 1482.505798798824,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 40.22865839038472,
          "uncertainty": 9.855626741889738,
          "unilateral_faults": 0,
          "wins": 25
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 116,
          "capped_draws": 108,
          "coverage_status": "rated",
          "distinct_rated_opponents": 56,
          "draws": 108,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-sonnet-5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 5,
          "model": "claude-sonnet-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-cf0ed4bbe4aaadd7",
          "rated_matches": 116,
          "raw_elo_rating": 1375.919697911772,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 30.049440212697277,
          "uncertainty": 2.4750163521024238,
          "unilateral_faults": 0,
          "wins": 3
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 120,
          "capped_draws": 96,
          "coverage_status": "rated",
          "distinct_rated_opponents": 53,
          "draws": 96,
          "evaluated_setting_identity": {
            "canonical_provider_route": "unknown_legacy",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "cohere/north-mini-code:free",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-11T17:22:09Z",
          "losses": 20,
          "model": "cohere/north-mini-code",
          "point_rating_method": "sequential_elo",
          "public_id": "E-c36a98e057c264eb",
          "rated_matches": 120,
          "raw_elo_rating": 1402.3296396091612,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 32.78188345286514,
          "uncertainty": 1.7045454545454586,
          "unilateral_faults": 0,
          "wins": 4
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 112,
          "capped_draws": 88,
          "coverage_status": "rated",
          "distinct_rated_opponents": 54,
          "draws": 88,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "deepseek/deepseek-v4-flash",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 18,
          "model": "deepseek/deepseek-v4-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-4375cf96eeb624e2",
          "rated_matches": 112,
          "raw_elo_rating": 1404.0594040768221,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "repaired",
          "score": 32.82885250240368,
          "uncertainty": 3.286043419179858,
          "unilateral_faults": 0,
          "wins": 6
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 108,
          "capped_draws": 82,
          "coverage_status": "rated",
          "distinct_rated_opponents": 53,
          "draws": 82,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "deepseek/deepseek-v4-pro",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 17,
          "model": "deepseek/deepseek-v4-pro",
          "point_rating_method": "sequential_elo",
          "public_id": "E-c296a7abab6975d7",
          "rated_matches": 108,
          "raw_elo_rating": 1516.1908415956534,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 44.09650651851254,
          "uncertainty": 4.1413142610575715,
          "unilateral_faults": 0,
          "wins": 9
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 0,
          "capped_draws": 0,
          "coverage_status": "pending",
          "distinct_rated_opponents": 0,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "low",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "google/gemini-3.5-flash",
            "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-21T14:20:15Z",
          "losses": 0,
          "model": "google/gemini-3.5-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-5aa593158b0d8b3a",
          "rated_matches": 0,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "low",
          "repair_status": "first_pass",
          "unilateral_faults": 0,
          "wins": 0
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 172,
          "capped_draws": 118,
          "coverage_status": "rated",
          "distinct_rated_opponents": 64,
          "draws": 118,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "minimal",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "google/gemini-3.5-flash-lite",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 47,
          "model": "google/gemini-3.5-flash-lite",
          "point_rating_method": "sequential_elo",
          "public_id": "E-284d554eca16e6f6",
          "rated_matches": 172,
          "raw_elo_rating": 1353.7438529638846,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "minimal",
          "repair_status": "first_pass",
          "score": 28.47149773278937,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 7
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 171,
          "capped_draws": 119,
          "coverage_status": "rated",
          "distinct_rated_opponents": 63,
          "draws": 119,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "minimal",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "google/gemini-3.5-flash-lite",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 45,
          "model": "google/gemini-3.5-flash-lite",
          "point_rating_method": "sequential_elo",
          "public_id": "E-af119b49b8f1d63d",
          "rated_matches": 171,
          "raw_elo_rating": 1345.626045326663,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "minimal",
          "repair_status": "first_pass",
          "score": 27.641837520102282,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 7
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 172,
          "capped_draws": 117,
          "coverage_status": "rated",
          "distinct_rated_opponents": 64,
          "draws": 117,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "minimal",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "google/gemini-3.6-flash",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 48,
          "model": "google/gemini-3.6-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-657c523bc9e9f80c",
          "rated_matches": 172,
          "raw_elo_rating": 1368.6850407942609,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "minimal",
          "repair_status": "repaired",
          "score": 29.982097403067577,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 7
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 174,
          "capped_draws": 121,
          "coverage_status": "rated",
          "distinct_rated_opponents": 65,
          "draws": 121,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "minimal",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "google/gemini-3.6-flash",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 44,
          "model": "google/gemini-3.6-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-c694a36a5e4e3f09",
          "rated_matches": 174,
          "raw_elo_rating": 1358.3892756425812,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "minimal",
          "repair_status": "first_pass",
          "score": 28.958784276838966,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 9
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 118,
          "capped_draws": 94,
          "coverage_status": "rated",
          "distinct_rated_opponents": 57,
          "draws": 94,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "google/gemma-4-31b-it",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 21,
          "model": "google/gemma-4-31b-it",
          "point_rating_method": "sequential_elo",
          "public_id": "E-8546650b7690a81a",
          "rated_matches": 118,
          "raw_elo_rating": 1415.9221194161503,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 34.12535861356842,
          "uncertainty": 2.084924851410568,
          "unilateral_faults": 0,
          "wins": 3
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 108,
          "capped_draws": 79,
          "coverage_status": "rated",
          "distinct_rated_opponents": 51,
          "draws": 79,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-4.1",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "omitted",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 16,
          "model": "gpt-4.1",
          "point_rating_method": "sequential_elo",
          "public_id": "E-eabc996d553eebe0",
          "rated_matches": 108,
          "raw_elo_rating": 1418.4565971654238,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "omitted",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 34.21527625173018,
          "uncertainty": 4.1413142610575715,
          "unilateral_faults": 0,
          "wins": 13
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 0,
          "capped_draws": 0,
          "coverage_status": "pending",
          "distinct_rated_opponents": 0,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "low",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5",
            "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-21T14:20:15Z",
          "losses": 0,
          "model": "gpt-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-ae3a897b3420bcfb",
          "rated_matches": 0,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "low",
          "repair_status": "first_pass",
          "unilateral_faults": 0,
          "wins": 0
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 95,
          "capped_draws": 55,
          "coverage_status": "rated",
          "distinct_rated_opponents": 42,
          "draws": 55,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.4",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 35,
          "model": "gpt-5.4",
          "point_rating_method": "sequential_elo",
          "public_id": "E-07ad6c481bf678a2",
          "rated_matches": 95,
          "raw_elo_rating": 1369.4284056978859,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "repaired",
          "score": 29.00442814379102,
          "uncertainty": 7.281036307982882,
          "unilateral_faults": 0,
          "wins": 5
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 106,
          "capped_draws": 74,
          "coverage_status": "rated",
          "distinct_rated_opponents": 52,
          "draws": 74,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.4",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 20,
          "model": "gpt-5.4",
          "point_rating_method": "sequential_elo",
          "public_id": "E-95f891d54f35bb4a",
          "rated_matches": 106,
          "raw_elo_rating": 1440.7096875631094,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "repaired",
          "score": 36.429097626212254,
          "uncertainty": 4.586824452283178,
          "unilateral_faults": 0,
          "wins": 12
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 92,
          "capped_draws": 77,
          "coverage_status": "rated",
          "distinct_rated_opponents": 45,
          "draws": 77,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.4-mini",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 13,
          "model": "gpt-5.4-mini",
          "point_rating_method": "sequential_elo",
          "public_id": "E-bb8ac98c284a38ce",
          "rated_matches": 90,
          "raw_elo_rating": 1400.3144399361822,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 32.01522338949161,
          "uncertainty": 8.664241836095918,
          "unilateral_faults": 2,
          "wins": 0
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 108,
          "capped_draws": 91,
          "coverage_status": "rated",
          "distinct_rated_opponents": 53,
          "draws": 91,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.4-nano",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-09T17:30:50Z",
          "losses": 17,
          "model": "gpt-5.4-nano",
          "point_rating_method": "sequential_elo",
          "public_id": "E-024aff0a983df40d",
          "rated_matches": 108,
          "raw_elo_rating": 1373.7536627261209,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 29.695673206034552,
          "uncertainty": 4.1413142610575715,
          "unilateral_faults": 0,
          "wins": 0
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 88,
          "capped_draws": 4,
          "coverage_status": "rated",
          "distinct_rated_opponents": 44,
          "draws": 4,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.4-nano",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 28,
          "model": "gpt-5.4-nano",
          "point_rating_method": "sequential_elo",
          "public_id": "E-fd5a36e5fd795426",
          "rated_matches": 88,
          "raw_elo_rating": 1679.920472976143,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "repaired",
          "score": 60.236877339102975,
          "uncertainty": 9.249894000318006,
          "unilateral_faults": 0,
          "wins": 56
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 106,
          "capped_draws": 83,
          "coverage_status": "rated",
          "distinct_rated_opponents": 51,
          "draws": 83,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 19,
          "model": "gpt-5.5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-c42fbee03a029c83",
          "rated_matches": 106,
          "raw_elo_rating": 1420.0693276623153,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 34.342294273323965,
          "uncertainty": 4.586824452283178,
          "unilateral_faults": 0,
          "wins": 4
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 108,
          "capped_draws": 89,
          "coverage_status": "rated",
          "distinct_rated_opponents": 53,
          "draws": 89,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.6-luna",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-10T05:30:29Z",
          "losses": 18,
          "model": "gpt-5.6-luna",
          "point_rating_method": "sequential_elo",
          "public_id": "E-8feb37d0677409f2",
          "rated_matches": 108,
          "raw_elo_rating": 1403.3240921912495,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 32.68533383456862,
          "uncertainty": 4.1413142610575715,
          "unilateral_faults": 0,
          "wins": 1
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 90,
          "capped_draws": 12,
          "coverage_status": "rated",
          "distinct_rated_opponents": 43,
          "draws": 12,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.6-luna",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 74,
          "model": "gpt-5.6-luna",
          "point_rating_method": "sequential_elo",
          "public_id": "E-b761803f2b99649c",
          "rated_matches": 90,
          "raw_elo_rating": 1083.655118803301,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 0.0,
          "uncertainty": 8.664241836095918,
          "unilateral_faults": 0,
          "wins": 4
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 92,
          "capped_draws": 15,
          "coverage_status": "rated",
          "distinct_rated_opponents": 46,
          "draws": 15,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.6-sol",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-10T05:30:29Z",
          "losses": 34,
          "model": "gpt-5.6-sol",
          "point_rating_method": "sequential_elo",
          "public_id": "E-994624d0bc2e266d",
          "rated_matches": 92,
          "raw_elo_rating": 1532.272527260815,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 45.402421187694905,
          "uncertainty": 8.09758473652126,
          "unilateral_faults": 0,
          "wins": 43
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 92,
          "capped_draws": 10,
          "coverage_status": "rated",
          "distinct_rated_opponents": 42,
          "draws": 10,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.6-sol",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 13,
          "model": "gpt-5.6-sol",
          "point_rating_method": "sequential_elo",
          "public_id": "E-9c0688f3432e6295",
          "rated_matches": 92,
          "raw_elo_rating": 1802.6772398837727,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 72.74116254930627,
          "uncertainty": 8.09758473652126,
          "unilateral_faults": 0,
          "wins": 69
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 102,
          "capped_draws": 74,
          "coverage_status": "rated",
          "distinct_rated_opponents": 50,
          "draws": 74,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.6-terra",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-10T05:30:29Z",
          "losses": 23,
          "model": "gpt-5.6-terra",
          "point_rating_method": "sequential_elo",
          "public_id": "E-44cace55a6126cdf",
          "rated_matches": 100,
          "raw_elo_rating": 1391.0357740645313,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 31.292461943857255,
          "uncertainty": 6.001859510499461,
          "unilateral_faults": 2,
          "wins": 3
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 160,
          "capped_draws": 140,
          "coverage_status": "rated",
          "distinct_rated_opponents": 57,
          "draws": 140,
          "evaluated_setting_identity": {
            "canonical_provider_route": "unknown_legacy",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "inclusionai/ling-3.0-flash:free",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 16,
          "model": "inclusionai/ling-3.0-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-11d1ae7d9526f835",
          "rated_matches": 156,
          "raw_elo_rating": 1377.9725394945106,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 30.768220146850258,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 0
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 158,
          "capped_draws": 132,
          "coverage_status": "rated",
          "distinct_rated_opponents": 61,
          "draws": 132,
          "evaluated_setting_identity": {
            "canonical_provider_route": "unknown_legacy",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "inclusionai/ling-3.0-flash:free",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 21,
          "model": "inclusionai/ling-3.0-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-28bcc8394e411616",
          "rated_matches": 158,
          "raw_elo_rating": 1365.25374003325,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "none",
          "repair_status": "repaired",
          "score": 29.50267408304644,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 5
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 114,
          "capped_draws": 103,
          "coverage_status": "rated",
          "distinct_rated_opponents": 54,
          "draws": 103,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "meituan/longcat-2.0",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 10,
          "model": "meituan/longcat-2.0",
          "point_rating_method": "sequential_elo",
          "public_id": "E-87d69837bf65e78b",
          "rated_matches": 114,
          "raw_elo_rating": 1374.243883454029,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 29.847639159936406,
          "uncertainty": 2.875240412015687,
          "unilateral_faults": 0,
          "wins": 1
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 116,
          "capped_draws": 97,
          "coverage_status": "rated",
          "distinct_rated_opponents": 55,
          "draws": 97,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "meituan/longcat-2.0",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 12,
          "model": "meituan/longcat-2.0",
          "point_rating_method": "sequential_elo",
          "public_id": "E-df8e0fab4bf8bb33",
          "rated_matches": 116,
          "raw_elo_rating": 1399.6109186599392,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 32.44469490442338,
          "uncertainty": 2.4750163521024238,
          "unilateral_faults": 0,
          "wins": 7
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 90,
          "capped_draws": 4,
          "coverage_status": "rated",
          "distinct_rated_opponents": 42,
          "draws": 4,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "minimal",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "meta/muse-spark-1.2",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-08-13T16:58:34Z",
          "losses": 33,
          "model": "meta/muse-spark-1.2",
          "point_rating_method": "sequential_elo",
          "public_id": "E-20b4e41aba8e4f47",
          "rated_matches": 90,
          "raw_elo_rating": 1653.2616124943645,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "minimal",
          "repair_status": "first_pass",
          "score": 57.58895419336781,
          "uncertainty": 8.664241836095918,
          "unilateral_faults": 0,
          "wins": 53
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 96,
          "capped_draws": 7,
          "coverage_status": "rated",
          "distinct_rated_opponents": 48,
          "draws": 7,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "minimax/minimax-m3",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 49,
          "model": "minimax/minimax-m3",
          "point_rating_method": "sequential_elo",
          "public_id": "E-e67e41d4491d7ad3",
          "rated_matches": 96,
          "raw_elo_rating": 1508.5181338037046,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 43.08815494051834,
          "uncertainty": 7.017308256680951,
          "unilateral_faults": 0,
          "wins": 40
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 116,
          "capped_draws": 92,
          "coverage_status": "rated",
          "distinct_rated_opponents": 58,
          "draws": 92,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "mistralai/mistral-medium-3-5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 22,
          "model": "mistralai/mistral-medium-3-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-ba85be2fa53925f5",
          "rated_matches": 116,
          "raw_elo_rating": 1354.8843322134849,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 27.922700568650274,
          "uncertainty": 2.4750163521024238,
          "unilateral_faults": 0,
          "wins": 2
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 178,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 70,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "low",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "moonshotai/kimi-k3",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T14:00:00Z",
          "losses": 8,
          "model": "moonshotai/kimi-k3",
          "point_rating_method": "sequential_elo",
          "public_id": "E-3e1be56b9d966ded",
          "rated_matches": 178,
          "raw_elo_rating": 2021.4459228627536,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "low",
          "repair_status": "first_pass",
          "score": 96.03018425662745,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 170
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 110,
          "capped_draws": 96,
          "coverage_status": "rated",
          "distinct_rated_opponents": 54,
          "draws": 96,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "nex-agi/nex-n2-pro",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-11T17:22:09Z",
          "losses": 14,
          "model": "nex-agi/nex-n2-pro",
          "point_rating_method": "sequential_elo",
          "public_id": "E-506d972b5c69a00d",
          "rated_matches": 110,
          "raw_elo_rating": 1403.0243582764076,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "none",
          "repair_status": "repaired",
          "score": 32.69008544176368,
          "uncertainty": 3.707899787624953,
          "unilateral_faults": 0,
          "wins": 0
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 84,
          "capped_draws": 78,
          "coverage_status": "rated",
          "distinct_rated_opponents": 42,
          "draws": 78,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "nvidia/nemotron-3-ultra-550b-a55b",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 5,
          "model": "nvidia/nemotron-3-ultra-550b-a55b",
          "point_rating_method": "sequential_elo",
          "public_id": "E-ada32b27ea6ffedd",
          "rated_matches": 84,
          "raw_elo_rating": 1422.0047853601131,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 34.06110906673491,
          "uncertainty": 10.482614454664043,
          "unilateral_faults": 0,
          "wins": 1
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 163,
          "capped_draws": 111,
          "coverage_status": "rated",
          "distinct_rated_opponents": 64,
          "draws": 111,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "low",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "o3",
            "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-21T14:20:15Z",
          "losses": 47,
          "model": "o3",
          "point_rating_method": "sequential_elo",
          "public_id": "E-335ae90fdc702bd6",
          "rated_matches": 163,
          "raw_elo_rating": 1346.4376685189152,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "low",
          "repair_status": "first_pass",
          "score": 27.649580485211807,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 5
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 158,
          "capped_draws": 94,
          "coverage_status": "rated",
          "distinct_rated_opponents": 66,
          "draws": 94,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "low",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "openai/gpt-oss-120b",
            "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-21T14:20:15Z",
          "losses": 60,
          "model": "openai/gpt-oss-120b",
          "point_rating_method": "sequential_elo",
          "public_id": "E-f6e9da46c61ad315",
          "rated_matches": 158,
          "raw_elo_rating": 1270.3817645663387,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "low",
          "repair_status": "first_pass",
          "score": 19.910827940292407,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 4
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 116,
          "capped_draws": 100,
          "coverage_status": "rated",
          "distinct_rated_opponents": 55,
          "draws": 100,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "poolside/laguna-s-2.1",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 13,
          "model": "poolside/laguna-s-2.1",
          "point_rating_method": "sequential_elo",
          "public_id": "E-4030acdbccf3ca03",
          "rated_matches": 116,
          "raw_elo_rating": 1380.5080334570664,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "none",
          "repair_status": "repaired",
          "score": 30.51333493382221,
          "uncertainty": 2.4750163521024238,
          "unilateral_faults": 0,
          "wins": 3
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 114,
          "capped_draws": 95,
          "coverage_status": "rated",
          "distinct_rated_opponents": 54,
          "draws": 95,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "poolside/laguna-s-2.1",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 16,
          "model": "poolside/laguna-s-2.1",
          "point_rating_method": "sequential_elo",
          "public_id": "E-e90a3ce84847ba43",
          "rated_matches": 114,
          "raw_elo_rating": 1386.4592518812346,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 31.08265017297974,
          "uncertainty": 2.875240412015687,
          "unilateral_faults": 0,
          "wins": 3
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 110,
          "capped_draws": 76,
          "coverage_status": "rated",
          "distinct_rated_opponents": 54,
          "draws": 76,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "qwen/qwen3.7-max",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 30,
          "model": "qwen/qwen3.7-max",
          "point_rating_method": "sequential_elo",
          "public_id": "E-a667eb7d15f7f43e",
          "rated_matches": 110,
          "raw_elo_rating": 1397.181675768906,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 32.09937241616148,
          "uncertainty": 3.707899787624953,
          "unilateral_faults": 0,
          "wins": 4
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 16,
          "capped_draws": 13,
          "coverage_status": "under_covered",
          "distinct_rated_opponents": 7,
          "draws": 13,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "minimal",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "qwen/qwen3.8-max",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 0,
          "model": "qwen/qwen3.8-max",
          "point_rating_method": "sequential_elo",
          "public_id": "E-e77a22943f077d4d",
          "rated_matches": 16,
          "raw_elo_rating": 1535.5507689243868,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "minimal",
          "repair_status": "first_pass",
          "score": 40.11898397519311,
          "uncertainty": 77.5178125181665,
          "unilateral_faults": 0,
          "wins": 3
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 14,
          "capped_draws": 5,
          "coverage_status": "rated",
          "distinct_rated_opponents": 7,
          "draws": 5,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "low",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "stealth/ox-alpha",
            "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-08-22T00:27:26Z",
          "losses": 9,
          "model": "stealth/ox-alpha",
          "point_rating_method": "sequential_elo",
          "public_id": "E-4e4d3135cae0253d",
          "rated_matches": 14,
          "raw_elo_rating": 1392.9698450978076,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "low",
          "repair_status": "first_pass",
          "score": 25.0701760707554,
          "uncertainty": 85.34944487358055,
          "unilateral_faults": 0,
          "wins": 0
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 14,
          "capped_draws": 6,
          "coverage_status": "rated",
          "distinct_rated_opponents": 7,
          "draws": 6,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "low",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "stealth/ox-alpha",
            "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-08-22T00:27:26Z",
          "losses": 8,
          "model": "stealth/ox-alpha",
          "point_rating_method": "sequential_elo",
          "public_id": "E-6b99e270ec28f9cf",
          "rated_matches": 14,
          "raw_elo_rating": 1403.200935100437,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "low",
          "repair_status": "first_pass",
          "score": 26.104570481696243,
          "uncertainty": 85.34944487358055,
          "unilateral_faults": 0,
          "wins": 0
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 158,
          "capped_draws": 104,
          "coverage_status": "rated",
          "distinct_rated_opponents": 66,
          "draws": 104,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "low",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "stepfun/step-3.7-flash",
            "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-21T14:20:15Z",
          "losses": 54,
          "model": "stepfun/step-3.7-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-c38fe2712e69333b",
          "rated_matches": 158,
          "raw_elo_rating": 1292.208218512245,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "low",
          "repair_status": "first_pass",
          "score": 22.117549019522556,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 0
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 114,
          "capped_draws": 90,
          "coverage_status": "rated",
          "distinct_rated_opponents": 55,
          "draws": 90,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "tencent/hy3-preview",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 21,
          "model": "tencent/hy3-preview",
          "point_rating_method": "sequential_elo",
          "public_id": "E-56487337fad4192f",
          "rated_matches": 114,
          "raw_elo_rating": 1417.9497965630508,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 34.26644030755798,
          "uncertainty": 2.875240412015687,
          "unilateral_faults": 0,
          "wins": 3
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 114,
          "capped_draws": 7,
          "coverage_status": "rated",
          "distinct_rated_opponents": 55,
          "draws": 7,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "thinkingmachines/inkling",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 37,
          "model": "thinkingmachines/inkling",
          "point_rating_method": "sequential_elo",
          "public_id": "E-68669040dc891a7d",
          "rated_matches": 114,
          "raw_elo_rating": 1751.0420667004444,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "repaired",
          "score": 67.94308497290339,
          "uncertainty": 2.875240412015687,
          "unilateral_faults": 0,
          "wins": 70
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 14,
          "capped_draws": 10,
          "coverage_status": "under_covered",
          "distinct_rated_opponents": 6,
          "draws": 10,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "thinkingmachines/inkling-small",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 4,
          "model": "thinkingmachines/inkling-small",
          "point_rating_method": "sequential_elo",
          "public_id": "E-99211d414b6fcc51",
          "rated_matches": 14,
          "raw_elo_rating": 1452.7011179104888,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "repaired",
          "score": 31.109189972494256,
          "uncertainty": 85.34944487358055,
          "unilateral_faults": 0,
          "wins": 0
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 174,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 72,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "low",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "x-ai/grok-4.5",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T14:00:00Z",
          "losses": 27,
          "model": "x-ai/grok-4.5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-b914d026c7631fcb",
          "rated_matches": 174,
          "raw_elo_rating": 1900.781455166142,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "low",
          "repair_status": "first_pass",
          "score": 83.79628828599199,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 147
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 96,
          "capped_draws": 60,
          "coverage_status": "rated",
          "distinct_rated_opponents": 48,
          "draws": 60,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "xiaomi/mimo-v2.5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 34,
          "model": "xiaomi/mimo-v2.5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-cabbf604f15eb575",
          "rated_matches": 96,
          "raw_elo_rating": 1302.9215821989426,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 22.301716366131743,
          "uncertainty": 7.017308256680951,
          "unilateral_faults": 0,
          "wins": 2
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 92,
          "capped_draws": 74,
          "coverage_status": "rated",
          "distinct_rated_opponents": 46,
          "draws": 74,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "xiaomi/mimo-v2.5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-01T00:15:48Z",
          "losses": 16,
          "model": "xiaomi/mimo-v2.5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-d51fce0298267f96",
          "rated_matches": 92,
          "raw_elo_rating": 1393.1451787133317,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 31.33622181797477,
          "uncertainty": 8.09758473652126,
          "unilateral_faults": 0,
          "wins": 2
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 80,
          "capped_draws": 64,
          "coverage_status": "rated",
          "distinct_rated_opponents": 40,
          "draws": 64,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "z-ai/glm-5.2",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-11T14:00:45Z",
          "losses": 13,
          "model": "z-ai/glm-5.2",
          "point_rating_method": "sequential_elo",
          "public_id": "E-6a361d88d8c1fb48",
          "rated_matches": 80,
          "raw_elo_rating": 1412.8311491297252,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 33.0266237531847,
          "uncertainty": 11.805555555555554,
          "unilateral_faults": 0,
          "wins": 3
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 70,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 35,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "z-ai/glm-5.2",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 18,
          "model": "z-ai/glm-5.2",
          "point_rating_method": "sequential_elo",
          "public_id": "E-97efd9455394f6d7",
          "rated_matches": 70,
          "raw_elo_rating": 1760.0879406666484,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "repaired",
          "score": 67.82932381706101,
          "uncertainty": 15.58908290969266,
          "unilateral_faults": 0,
          "wins": 52
        }
      ]
    },
    "full_freedom/intensive": {
      "GB2-01": [
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 102,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 47,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "xhigh",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-fable-5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-03T17:50:00Z",
          "losses": 35,
          "model": "claude-fable-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-8000131e469a8bb6",
          "rated_matches": 102,
          "raw_elo_rating": 1824.3873130220802,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "xhigh",
          "repair_status": "first_pass",
          "score": 79.58869492247467,
          "uncertainty": 5.516463908214657,
          "unilateral_faults": 0,
          "wins": 67
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 0,
          "capped_draws": 0,
          "coverage_status": "pending",
          "distinct_rated_opponents": 0,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "legacy_shared_thinking_budget",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-opus-4-5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "budget",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 0,
          "model": "claude-opus-4-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-53c8add70ed7d2e7",
          "rated_matches": 0,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "budget",
          "reasoning_setting": "legacy_shared_thinking_budget",
          "repair_status": "first_pass",
          "unilateral_faults": 0,
          "wins": 0
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 153,
          "capped_draws": 26,
          "coverage_status": "rated",
          "distinct_rated_opponents": 60,
          "draws": 26,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-opus-4-5",
            "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 36,
          "model": "claude-opus-4-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-5b675f86b98132f4",
          "rated_matches": 153,
          "raw_elo_rating": 1662.883091394821,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "first_pass",
          "score": 63.991356251926845,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 91
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 108,
          "capped_draws": 18,
          "coverage_status": "rated",
          "distinct_rated_opponents": 49,
          "draws": 18,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "xhigh",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-opus-4-8",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-03T17:20:00Z",
          "losses": 36,
          "model": "claude-opus-4-8",
          "point_rating_method": "sequential_elo",
          "public_id": "E-3308d2952452916e",
          "rated_matches": 108,
          "raw_elo_rating": 1609.684924746103,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "xhigh",
          "repair_status": "first_pass",
          "score": 58.000169538136674,
          "uncertainty": 4.1413142610575715,
          "unilateral_faults": 0,
          "wins": 54
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 70,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 29,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "xhigh",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-opus-5",
            "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-25T15:48:00Z",
          "losses": 18,
          "model": "claude-opus-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-700f3dddd611df07",
          "rated_matches": 70,
          "raw_elo_rating": 1853.021779157713,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "xhigh",
          "repair_status": "first_pass",
          "score": 81.66832408200672,
          "uncertainty": 15.58908290969266,
          "unilateral_faults": 0,
          "wins": 52
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 58,
          "capped_draws": 2,
          "coverage_status": "rated",
          "distinct_rated_opponents": 28,
          "draws": 2,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "xhigh",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-opus-5",
            "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-25T15:48:00Z",
          "losses": 29,
          "model": "claude-opus-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-bf06fe9df8858291",
          "rated_matches": 58,
          "raw_elo_rating": 1467.974430458784,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "xhigh",
          "repair_status": "first_pass",
          "score": 42.28669895236079,
          "uncertainty": 21.344455490411935,
          "unilateral_faults": 0,
          "wins": 27
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 90,
          "capped_draws": 14,
          "coverage_status": "rated",
          "distinct_rated_opponents": 42,
          "draws": 14,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "xhigh",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-sonnet-5",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 28,
          "model": "claude-sonnet-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-41b4bf40efe85b59",
          "rated_matches": 90,
          "raw_elo_rating": 1604.7460346224086,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "xhigh",
          "repair_status": "first_pass",
          "score": 57.13530033302503,
          "uncertainty": 8.664241836095918,
          "unilateral_faults": 0,
          "wins": 48
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 102,
          "capped_draws": 18,
          "coverage_status": "rated",
          "distinct_rated_opponents": 50,
          "draws": 18,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "xhigh",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-sonnet-5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-03T16:50:00Z",
          "losses": 34,
          "model": "claude-sonnet-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-5e353d79b07fa294",
          "rated_matches": 102,
          "raw_elo_rating": 1695.23469264125,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "xhigh",
          "repair_status": "first_pass",
          "score": 66.53539430743486,
          "uncertainty": 5.516463908214657,
          "unilateral_faults": 0,
          "wins": 50
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 94,
          "capped_draws": 18,
          "coverage_status": "rated",
          "distinct_rated_opponents": 45,
          "draws": 18,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "xhigh",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "deepseek/deepseek-v4-flash",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 51,
          "model": "deepseek/deepseek-v4-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-b9882650a0cde9ac",
          "rated_matches": 94,
          "raw_elo_rating": 1353.1558761739786,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "xhigh",
          "repair_status": "first_pass",
          "score": 31.797564014719292,
          "uncertainty": 7.54891760425771,
          "unilateral_faults": 0,
          "wins": 25
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 100,
          "capped_draws": 19,
          "coverage_status": "rated",
          "distinct_rated_opponents": 49,
          "draws": 19,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "xhigh",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "deepseek/deepseek-v4-pro",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 48,
          "model": "deepseek/deepseek-v4-pro",
          "point_rating_method": "sequential_elo",
          "public_id": "E-e192048d4eaa3c43",
          "rated_matches": 100,
          "raw_elo_rating": 1453.8732003554912,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "xhigh",
          "repair_status": "repaired",
          "score": 42.10203075533094,
          "uncertainty": 6.001859510499461,
          "unilateral_faults": 0,
          "wins": 33
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 140,
          "capped_draws": 28,
          "coverage_status": "rated",
          "distinct_rated_opponents": 49,
          "draws": 28,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "google/gemini-3.5-flash-lite",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 78,
          "model": "google/gemini-3.5-flash-lite",
          "point_rating_method": "sequential_elo",
          "public_id": "E-85d9dd9fbf531322",
          "rated_matches": 140,
          "raw_elo_rating": 1318.8398191425192,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "first_pass",
          "score": 29.072445927965525,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 34
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 145,
          "capped_draws": 17,
          "coverage_status": "rated",
          "distinct_rated_opponents": 59,
          "draws": 17,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "google/gemini-3.6-flash",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 39,
          "model": "google/gemini-3.6-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-df0493ecef384a6a",
          "rated_matches": 144,
          "raw_elo_rating": 1710.9348856205506,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "first_pass",
          "score": 68.74831312733114,
          "uncertainty": 0.0,
          "unilateral_faults": 1,
          "wins": 88
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 178,
          "capped_draws": 75,
          "coverage_status": "rated",
          "distinct_rated_opponents": 67,
          "draws": 75,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "google/gemini-3.6-flash",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 78,
          "model": "google/gemini-3.6-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-e9260a0da3a64563",
          "rated_matches": 178,
          "raw_elo_rating": 1328.4998934490186,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "repaired",
          "score": 30.431694719824712,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 25
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 110,
          "capped_draws": 6,
          "coverage_status": "rated",
          "distinct_rated_opponents": 52,
          "draws": 6,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 54,
          "model": "gpt-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-3e63b136f656e976",
          "rated_matches": 110,
          "raw_elo_rating": 1508.6425409214996,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "first_pass",
          "score": 47.822980600607565,
          "uncertainty": 3.707899787624953,
          "unilateral_faults": 0,
          "wins": 50
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 98,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 47,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "xhigh",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.4",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 5,
          "model": "gpt-5.4",
          "point_rating_method": "sequential_elo",
          "public_id": "E-5d8a6b14c27539ab",
          "rated_matches": 98,
          "raw_elo_rating": 2015.429236982834,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "xhigh",
          "repair_status": "first_pass",
          "score": 98.8173965766658,
          "uncertainty": 6.501890762960602,
          "unilateral_faults": 0,
          "wins": 93
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 94,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 42,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "xhigh",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.4",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 3,
          "model": "gpt-5.4",
          "point_rating_method": "sequential_elo",
          "public_id": "E-9879a37f54e31cff",
          "rated_matches": 94,
          "raw_elo_rating": 1979.430767061083,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "xhigh",
          "repair_status": "first_pass",
          "score": 95.09441694960572,
          "uncertainty": 7.54891760425771,
          "unilateral_faults": 0,
          "wins": 91
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 100,
          "capped_draws": 30,
          "coverage_status": "rated",
          "distinct_rated_opponents": 46,
          "draws": 30,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "xhigh",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 16,
          "model": "gpt-5.5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-8c61292c31db2722",
          "rated_matches": 100,
          "raw_elo_rating": 1756.676617437372,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "xhigh",
          "repair_status": "first_pass",
          "score": 72.70600935658693,
          "uncertainty": 6.001859510499461,
          "unilateral_faults": 0,
          "wins": 54
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 98,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 47,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "xhigh",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.6-luna",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-10T05:30:29Z",
          "losses": 32,
          "model": "gpt-5.6-luna",
          "point_rating_method": "sequential_elo",
          "public_id": "E-38187ed58fb76057",
          "rated_matches": 98,
          "raw_elo_rating": 1832.8760948770332,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "xhigh",
          "repair_status": "first_pass",
          "score": 80.36696920553993,
          "uncertainty": 6.501890762960602,
          "unilateral_faults": 0,
          "wins": 66
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 90,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 42,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "xhigh",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.6-luna",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 20,
          "model": "gpt-5.6-luna",
          "point_rating_method": "sequential_elo",
          "public_id": "E-65def22b992d7636",
          "rated_matches": 90,
          "raw_elo_rating": 1836.192748563626,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "xhigh",
          "repair_status": "first_pass",
          "score": 80.5273424342959,
          "uncertainty": 8.664241836095918,
          "unilateral_faults": 0,
          "wins": 70
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 104,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 47,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "xhigh",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.6-sol",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-10T05:30:29Z",
          "losses": 23,
          "model": "gpt-5.6-sol",
          "point_rating_method": "sequential_elo",
          "public_id": "E-9e683b3cd6c7f7c3",
          "rated_matches": 104,
          "raw_elo_rating": 1852.6117511208768,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "xhigh",
          "repair_status": "first_pass",
          "score": 82.47942500679652,
          "uncertainty": 5.045003647426665,
          "unilateral_faults": 0,
          "wins": 81
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 92,
          "capped_draws": 3,
          "coverage_status": "rated",
          "distinct_rated_opponents": 42,
          "draws": 3,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "xhigh",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.6-sol",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 21,
          "model": "gpt-5.6-sol",
          "point_rating_method": "sequential_elo",
          "public_id": "E-ecb408c0fdea8489",
          "rated_matches": 92,
          "raw_elo_rating": 1743.8724255296063,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "xhigh",
          "repair_status": "first_pass",
          "score": 71.24245506978434,
          "uncertainty": 8.09758473652126,
          "unilateral_faults": 0,
          "wins": 68
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 102,
          "capped_draws": 31,
          "coverage_status": "rated",
          "distinct_rated_opponents": 47,
          "draws": 31,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "xhigh",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.6-terra",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-10T05:30:29Z",
          "losses": 42,
          "model": "gpt-5.6-terra",
          "point_rating_method": "sequential_elo",
          "public_id": "E-36d36f4895d90b11",
          "rated_matches": 102,
          "raw_elo_rating": 1446.6406737765797,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "xhigh",
          "repair_status": "first_pass",
          "score": 41.410294640288974,
          "uncertainty": 5.516463908214657,
          "unilateral_faults": 0,
          "wins": 29
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 90,
          "capped_draws": 7,
          "coverage_status": "rated",
          "distinct_rated_opponents": 44,
          "draws": 7,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "xhigh",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "meta/muse-spark-1.2",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-08-13T16:58:34Z",
          "losses": 37,
          "model": "meta/muse-spark-1.2",
          "point_rating_method": "sequential_elo",
          "public_id": "E-60e0feec8e72ba89",
          "rated_matches": 90,
          "raw_elo_rating": 1571.9644721957648,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "xhigh",
          "repair_status": "first_pass",
          "score": 53.82210709138648,
          "uncertainty": 8.664241836095918,
          "unilateral_faults": 0,
          "wins": 46
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 90,
          "capped_draws": 19,
          "coverage_status": "rated",
          "distinct_rated_opponents": 43,
          "draws": 19,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "mistralai/mistral-medium-3-5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 63,
          "model": "mistralai/mistral-medium-3-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-99c7b0d758665b66",
          "rated_matches": 90,
          "raw_elo_rating": 1152.0261703164747,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "first_pass",
          "score": 11.379446013072632,
          "uncertainty": 8.664241836095918,
          "unilateral_faults": 0,
          "wins": 8
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 174,
          "capped_draws": 17,
          "coverage_status": "rated",
          "distinct_rated_opponents": 69,
          "draws": 17,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "max",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "moonshotai/kimi-k3",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T14:00:00Z",
          "losses": 59,
          "model": "moonshotai/kimi-k3",
          "point_rating_method": "sequential_elo",
          "public_id": "E-dbb89dcf5242a5a0",
          "rated_matches": 174,
          "raw_elo_rating": 1633.9448139210695,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "max",
          "repair_status": "repaired",
          "score": 61.26830836120785,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 98
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 94,
          "capped_draws": 20,
          "coverage_status": "rated",
          "distinct_rated_opponents": 47,
          "draws": 20,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "nvidia/nemotron-3-ultra-550b-a55b",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-11T17:22:09Z",
          "losses": 52,
          "model": "nvidia/nemotron-3-ultra-550b-a55b",
          "point_rating_method": "sequential_elo",
          "public_id": "E-ce064a9927030b28",
          "rated_matches": 94,
          "raw_elo_rating": 1402.8528152679808,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "repaired",
          "score": 36.82037411124304,
          "uncertainty": 7.54891760425771,
          "unilateral_faults": 0,
          "wins": 22
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 162,
          "capped_draws": 6,
          "coverage_status": "rated",
          "distinct_rated_opponents": 59,
          "draws": 6,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "o3",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-03T15:45:00Z",
          "losses": 50,
          "model": "o3",
          "point_rating_method": "sequential_elo",
          "public_id": "E-01ad69b67b42a9e7",
          "rated_matches": 162,
          "raw_elo_rating": 1645.9887791241347,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "first_pass",
          "score": 62.37508300091857,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 106
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 152,
          "capped_draws": 1,
          "coverage_status": "rated",
          "distinct_rated_opponents": 60,
          "draws": 1,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "o3",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-03T16:00:00Z",
          "losses": 49,
          "model": "o3",
          "point_rating_method": "sequential_elo",
          "public_id": "E-21b0558e9f2190f7",
          "rated_matches": 152,
          "raw_elo_rating": 1713.877626060037,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "first_pass",
          "score": 69.13468390025471,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 102
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 132,
          "capped_draws": 25,
          "coverage_status": "rated",
          "distinct_rated_opponents": 50,
          "draws": 25,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "o3",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-03T15:50:00Z",
          "losses": 62,
          "model": "o3",
          "point_rating_method": "sequential_elo",
          "public_id": "E-5e8b87fcfa2225fd",
          "rated_matches": 132,
          "raw_elo_rating": 1412.3908545550473,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "first_pass",
          "score": 38.42663779921314,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 45
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 0,
          "capped_draws": 0,
          "coverage_status": "pending",
          "distinct_rated_opponents": 0,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "xhigh",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "qwen/qwen3.8-max",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 0,
          "model": "qwen/qwen3.8-max",
          "point_rating_method": "sequential_elo",
          "public_id": "E-06acc10727220528",
          "rated_matches": 0,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "xhigh",
          "repair_status": "first_pass",
          "unilateral_faults": 0,
          "wins": 0
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 14,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 7,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "max",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "stealth/ox-alpha",
            "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-08-22T00:27:26Z",
          "losses": 1,
          "model": "stealth/ox-alpha",
          "point_rating_method": "sequential_elo",
          "public_id": "E-3869622aa388e835",
          "rated_matches": 14,
          "raw_elo_rating": 1643.1131365588276,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "max",
          "repair_status": "first_pass",
          "score": 54.81263208060843,
          "uncertainty": 85.34944487358055,
          "unilateral_faults": 0,
          "wins": 13
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 14,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 7,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "max",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "stealth/ox-alpha",
            "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-08-22T00:27:26Z",
          "losses": 9,
          "model": "stealth/ox-alpha",
          "point_rating_method": "sequential_elo",
          "public_id": "E-dc2b7cd047c7694a",
          "rated_matches": 14,
          "raw_elo_rating": 1448.9187433283219,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "max",
          "repair_status": "first_pass",
          "score": 35.18563740470879,
          "uncertainty": 85.34944487358055,
          "unilateral_faults": 0,
          "wins": 5
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 14,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 7,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "max",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "stealth/ox-alpha",
            "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-08-22T00:27:26Z",
          "losses": 6,
          "model": "stealth/ox-alpha",
          "point_rating_method": "sequential_elo",
          "public_id": "E-e70cadce2bb0e8b1",
          "rated_matches": 14,
          "raw_elo_rating": 1530.6472757303504,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "max",
          "repair_status": "first_pass",
          "score": 43.445842262527115,
          "uncertainty": 85.34944487358055,
          "unilateral_faults": 0,
          "wins": 8
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 82,
          "capped_draws": 6,
          "coverage_status": "rated",
          "distinct_rated_opponents": 41,
          "draws": 6,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "stepfun/step-3.7-flash",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 62,
          "model": "stepfun/step-3.7-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-4b0ce2bc67b08d8a",
          "rated_matches": 82,
          "raw_elo_rating": 1165.3075653397077,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "repaired",
          "score": 12.522239497043625,
          "uncertainty": 11.132129994845172,
          "unilateral_faults": 0,
          "wins": 14
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 102,
          "capped_draws": 18,
          "coverage_status": "rated",
          "distinct_rated_opponents": 51,
          "draws": 18,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "tencent/hy3-preview",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 39,
          "model": "tencent/hy3-preview",
          "point_rating_method": "sequential_elo",
          "public_id": "E-29e8870e43d717e5",
          "rated_matches": 102,
          "raw_elo_rating": 1614.8727554112447,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "first_pass",
          "score": 58.41330958645064,
          "uncertainty": 5.516463908214657,
          "unilateral_faults": 0,
          "wins": 45
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 142,
          "capped_draws": 53,
          "coverage_status": "rated",
          "distinct_rated_opponents": 50,
          "draws": 53,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "max",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "thinkingmachines/inkling",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 83,
          "model": "thinkingmachines/inkling",
          "point_rating_method": "sequential_elo",
          "public_id": "E-ab1de1dc51400446",
          "rated_matches": 142,
          "raw_elo_rating": 1200.6961116510595,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "max",
          "repair_status": "first_pass",
          "score": 17.155695255029734,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 6
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 0,
          "capped_draws": 0,
          "coverage_status": "pending",
          "distinct_rated_opponents": 0,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "max",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "thinkingmachines/inkling-small",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 0,
          "model": "thinkingmachines/inkling-small",
          "point_rating_method": "sequential_elo",
          "public_id": "E-40197ff2c5984de1",
          "rated_matches": 0,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "max",
          "repair_status": "first_pass",
          "unilateral_faults": 0,
          "wins": 0
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 170,
          "capped_draws": 32,
          "coverage_status": "rated",
          "distinct_rated_opponents": 66,
          "draws": 32,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "x-ai/grok-4.5",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T14:00:00Z",
          "losses": 19,
          "model": "x-ai/grok-4.5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-1c8e452ede41ea2e",
          "rated_matches": 170,
          "raw_elo_rating": 1829.172240589223,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "repaired",
          "score": 80.96417402361442,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 119
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 72,
          "capped_draws": 41,
          "coverage_status": "rated",
          "distinct_rated_opponents": 36,
          "draws": 41,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "xiaomi/mimo-v2.5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T06:10:40Z",
          "losses": 29,
          "model": "xiaomi/mimo-v2.5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-8478c64d84536b61",
          "rated_matches": 72,
          "raw_elo_rating": 1213.1687467409479,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "repaired",
          "score": 17.065325253973946,
          "uncertainty": 14.770573598065289,
          "unilateral_faults": 0,
          "wins": 2
        }
      ],
      "GB2-02": [
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 84,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 37,
          "draws": 37,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "xhigh",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-fable-5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-03T17:50:00Z",
          "losses": 4,
          "model": "claude-fable-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-f6a30e7d9986c9b8",
          "rated_matches": 84,
          "raw_elo_rating": 1705.9057480073943,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "xhigh",
          "repair_status": "first_pass",
          "score": 73.74954635252826,
          "uncertainty": 10.482614454664043,
          "unilateral_faults": 0,
          "wins": 43
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 0,
          "capped_draws": 0,
          "coverage_status": "pending",
          "distinct_rated_opponents": 0,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "legacy_shared_thinking_budget",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-opus-4-5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "budget",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 0,
          "model": "claude-opus-4-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-0454dbb9530f84f7",
          "rated_matches": 0,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "budget",
          "reasoning_setting": "legacy_shared_thinking_budget",
          "repair_status": "first_pass",
          "unilateral_faults": 0,
          "wins": 0
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 130,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 50,
          "draws": 107,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-opus-4-5",
            "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 22,
          "model": "claude-opus-4-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-63fde27ceab11930",
          "rated_matches": 130,
          "raw_elo_rating": 1428.2065730933373,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "first_pass",
          "score": 13.32462959183295,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 1
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 86,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 36,
          "draws": 32,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "xhigh",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-opus-4-8",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-03T17:20:00Z",
          "losses": 5,
          "model": "claude-opus-4-8",
          "point_rating_method": "sequential_elo",
          "public_id": "E-a81bd03e764818f6",
          "rated_matches": 86,
          "raw_elo_rating": 1739.7423942603561,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "xhigh",
          "repair_status": "first_pass",
          "score": 81.45539006883097,
          "uncertainty": 9.855626741889738,
          "unilateral_faults": 0,
          "wins": 49
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 58,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 22,
          "draws": 25,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "xhigh",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-opus-5",
            "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-25T15:48:01Z",
          "losses": 10,
          "model": "claude-opus-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-6b45cf5aebf0c66e",
          "rated_matches": 58,
          "raw_elo_rating": 1643.2395344365823,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "xhigh",
          "repair_status": "first_pass",
          "score": 57.73661660019647,
          "uncertainty": 21.344455490411935,
          "unilateral_faults": 0,
          "wins": 23
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 60,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 23,
          "draws": 13,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "xhigh",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-opus-5",
            "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-25T15:48:01Z",
          "losses": 11,
          "model": "claude-opus-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-fcdd98d74e80134a",
          "rated_matches": 60,
          "raw_elo_rating": 1754.756883936148,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "xhigh",
          "repair_status": "first_pass",
          "score": 82.95540018008184,
          "uncertainty": 20.268439966447993,
          "unilateral_faults": 0,
          "wins": 36
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 68,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 30,
          "draws": 62,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "xhigh",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-sonnet-5",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 5,
          "model": "claude-sonnet-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-d4d2fc700a2c74f1",
          "rated_matches": 68,
          "raw_elo_rating": 1463.1243014745253,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "xhigh",
          "repair_status": "first_pass",
          "score": 18.196918446623908,
          "uncertainty": 16.4429265428846,
          "unilateral_faults": 0,
          "wins": 1
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 82,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 38,
          "draws": 55,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "xhigh",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-sonnet-5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-03T16:50:00Z",
          "losses": 15,
          "model": "claude-sonnet-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-e35d82f3fd09a1f4",
          "rated_matches": 82,
          "raw_elo_rating": 1511.6295667779777,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "xhigh",
          "repair_status": "first_pass",
          "score": 30.035421839838055,
          "uncertainty": 11.132129994845172,
          "unilateral_faults": 0,
          "wins": 12
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 74,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 36,
          "draws": 59,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "xhigh",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "deepseek/deepseek-v4-flash",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 11,
          "model": "deepseek/deepseek-v4-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-12dcb25370550495",
          "rated_matches": 74,
          "raw_elo_rating": 1479.442621444907,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "xhigh",
          "repair_status": "repaired",
          "score": 22.300174477766653,
          "uncertainty": 13.985026918962571,
          "unilateral_faults": 0,
          "wins": 4
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 100,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 38,
          "draws": 81,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "google/gemini-3.5-flash-lite",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 8,
          "model": "google/gemini-3.5-flash-lite",
          "point_rating_method": "sequential_elo",
          "public_id": "E-423f6c31467b8943",
          "rated_matches": 100,
          "raw_elo_rating": 1493.463385992254,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "first_pass",
          "score": 26.879776376230204,
          "uncertainty": 6.001859510499461,
          "unilateral_faults": 0,
          "wins": 11
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 76,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 37,
          "draws": 58,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 16,
          "model": "gpt-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-5bccb9b671ce5eae",
          "rated_matches": 76,
          "raw_elo_rating": 1471.072947000906,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "first_pass",
          "score": 20.557432544949897,
          "uncertainty": 13.230288229818967,
          "unilateral_faults": 0,
          "wins": 2
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 82,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 36,
          "draws": 51,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "xhigh",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.4",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 9,
          "model": "gpt-5.4",
          "point_rating_method": "sequential_elo",
          "public_id": "E-4aa582caf9d9f6da",
          "rated_matches": 82,
          "raw_elo_rating": 1621.61381435049,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "xhigh",
          "repair_status": "first_pass",
          "score": 54.7169870956697,
          "uncertainty": 11.132129994845172,
          "unilateral_faults": 0,
          "wins": 22
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 66,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 31,
          "draws": 58,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "xhigh",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.6-luna",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 3,
          "model": "gpt-5.6-luna",
          "point_rating_method": "sequential_elo",
          "public_id": "E-02a02961ddfed4cf",
          "rated_matches": 66,
          "raw_elo_rating": 1500.3602776554874,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "xhigh",
          "repair_status": "first_pass",
          "score": 26.392941660287374,
          "uncertainty": 17.33472217815261,
          "unilateral_faults": 0,
          "wins": 5
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 88,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 44,
          "draws": 75,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "xhigh",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.6-luna",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-10T05:30:29Z",
          "losses": 10,
          "model": "gpt-5.6-luna",
          "point_rating_method": "sequential_elo",
          "public_id": "E-a30e455ba172d80e",
          "rated_matches": 88,
          "raw_elo_rating": 1467.0307143374596,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "xhigh",
          "repair_status": "repaired",
          "score": 20.364907326166584,
          "uncertainty": 9.249894000318006,
          "unilateral_faults": 0,
          "wins": 3
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 90,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 37,
          "draws": 15,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "xhigh",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.6-sol",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-10T05:30:29Z",
          "losses": 11,
          "model": "gpt-5.6-sol",
          "point_rating_method": "sequential_elo",
          "public_id": "E-33dc9365cfacf9c0",
          "rated_matches": 90,
          "raw_elo_rating": 1817.1768615381052,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "xhigh",
          "repair_status": "first_pass",
          "score": 99.04634600393882,
          "uncertainty": 8.664241836095918,
          "unilateral_faults": 0,
          "wins": 64
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 68,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 31,
          "draws": 13,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "xhigh",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.6-sol",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 0,
          "model": "gpt-5.6-sol",
          "point_rating_method": "sequential_elo",
          "public_id": "E-f939ae7c9b81e0cc",
          "rated_matches": 68,
          "raw_elo_rating": 1827.6494148740956,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "xhigh",
          "repair_status": "repaired",
          "score": 100.0,
          "uncertainty": 16.4429265428846,
          "unilateral_faults": 0,
          "wins": 55
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 90,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 37,
          "draws": 52,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "xhigh",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.6-terra",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-10T05:30:29Z",
          "losses": 20,
          "model": "gpt-5.6-terra",
          "point_rating_method": "sequential_elo",
          "public_id": "E-1b12482867c807c9",
          "rated_matches": 90,
          "raw_elo_rating": 1584.5440638410278,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "xhigh",
          "repair_status": "first_pass",
          "score": 46.84121932685183,
          "uncertainty": 8.664241836095918,
          "unilateral_faults": 0,
          "wins": 18
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 130,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 49,
          "draws": 112,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "max",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "moonshotai/kimi-k3",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T14:00:00Z",
          "losses": 12,
          "model": "moonshotai/kimi-k3",
          "point_rating_method": "sequential_elo",
          "public_id": "E-1beeecccf3f2c84f",
          "rated_matches": 130,
          "raw_elo_rating": 1474.3344994862955,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "max",
          "repair_status": "repaired",
          "score": 23.676197661918458,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 6
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 70,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 34,
          "draws": 62,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "nvidia/nemotron-3-ultra-550b-a55b",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 7,
          "model": "nvidia/nemotron-3-ultra-550b-a55b",
          "point_rating_method": "sequential_elo",
          "public_id": "E-2404d10bab26a254",
          "rated_matches": 70,
          "raw_elo_rating": 1474.5426351145522,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "repaired",
          "score": 20.912595566958643,
          "uncertainty": 15.58908290969266,
          "unilateral_faults": 0,
          "wins": 1
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 68,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 34,
          "draws": 56,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "nvidia/nemotron-3-ultra-550b-a55b",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-11T17:22:09Z",
          "losses": 11,
          "model": "nvidia/nemotron-3-ultra-550b-a55b",
          "point_rating_method": "sequential_elo",
          "public_id": "E-abd2cae3e3ff9bdb",
          "rated_matches": 68,
          "raw_elo_rating": 1460.7049054242543,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "repaired",
          "score": 17.653981773305354,
          "uncertainty": 16.4429265428846,
          "unilateral_faults": 0,
          "wins": 1
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 74,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 37,
          "draws": 59,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "openai/gpt-oss-120b",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 15,
          "model": "openai/gpt-oss-120b",
          "point_rating_method": "sequential_elo",
          "public_id": "E-e5b4a3586049e1c9",
          "rated_matches": 74,
          "raw_elo_rating": 1442.0685143240635,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "repaired",
          "score": 13.91305101107773,
          "uncertainty": 13.985026918962571,
          "unilateral_faults": 0,
          "wins": 0
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 17,
          "capped_draws": 0,
          "coverage_status": "under_covered",
          "distinct_rated_opponents": 9,
          "draws": 13,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "xhigh",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "qwen/qwen3.8-max",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-08-18T19:04:19Z",
          "losses": 1,
          "model": "qwen/qwen3.8-max",
          "point_rating_method": "sequential_elo",
          "public_id": "E-51f44e67337145d4",
          "rated_matches": 17,
          "raw_elo_rating": 1519.2581453563312,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "xhigh",
          "repair_status": "first_pass",
          "score": 20.442652389870492,
          "uncertainty": 74.10113019775793,
          "unilateral_faults": 0,
          "wins": 3
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 14,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 7,
          "draws": 6,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "max",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "stealth/ox-alpha",
            "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-08-22T00:27:26Z",
          "losses": 1,
          "model": "stealth/ox-alpha",
          "point_rating_method": "sequential_elo",
          "public_id": "E-844b5265eeccbffb",
          "rated_matches": 14,
          "raw_elo_rating": 1575.5462752401954,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "max",
          "repair_status": "first_pass",
          "score": 31.0548842909548,
          "uncertainty": 85.34944487358055,
          "unilateral_faults": 0,
          "wins": 7
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 14,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 7,
          "draws": 4,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "max",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "stealth/ox-alpha",
            "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-08-22T00:27:26Z",
          "losses": 0,
          "model": "stealth/ox-alpha",
          "point_rating_method": "sequential_elo",
          "public_id": "E-f1feaabe79bde601",
          "rated_matches": 14,
          "raw_elo_rating": 1614.7168198608954,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "max",
          "repair_status": "first_pass",
          "score": 39.84514630120195,
          "uncertainty": 85.34944487358055,
          "unilateral_faults": 0,
          "wins": 10
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 68,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 32,
          "draws": 53,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "tencent/hy3-preview",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 12,
          "model": "tencent/hy3-preview",
          "point_rating_method": "sequential_elo",
          "public_id": "E-fbf6af15f65f01d7",
          "rated_matches": 66,
          "raw_elo_rating": 1444.0591535680944,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "repaired",
          "score": 13.758406271721789,
          "uncertainty": 17.33472217815261,
          "unilateral_faults": 2,
          "wins": 1
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 124,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 43,
          "draws": 111,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "max",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "thinkingmachines/inkling",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 9,
          "model": "thinkingmachines/inkling",
          "point_rating_method": "sequential_elo",
          "public_id": "E-9468e854340a4e9b",
          "rated_matches": 122,
          "raw_elo_rating": 1459.031259226249,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "max",
          "repair_status": "repaired",
          "score": 19.990967262210003,
          "uncertainty": 1.3334817333716131,
          "unilateral_faults": 0,
          "wins": 2
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 16,
          "capped_draws": 0,
          "coverage_status": "under_covered",
          "distinct_rated_opponents": 9,
          "draws": 15,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "max",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "thinkingmachines/inkling-small",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 1,
          "model": "thinkingmachines/inkling-small",
          "point_rating_method": "sequential_elo",
          "public_id": "E-d92a785d012f8e1b",
          "rated_matches": 16,
          "raw_elo_rating": 1482.473546162997,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "max",
          "repair_status": "first_pass",
          "score": 11.574430248545012,
          "uncertainty": 77.5178125181665,
          "unilateral_faults": 0,
          "wins": 0
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 144,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 53,
          "draws": 72,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "x-ai/grok-4.5",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T14:00:00Z",
          "losses": 24,
          "model": "x-ai/grok-4.5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-0576181f89efa7a7",
          "rated_matches": 144,
          "raw_elo_rating": 1594.752196706652,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "repaired",
          "score": 51.08735602238606,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 48
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 74,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 37,
          "draws": 60,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "xiaomi/mimo-v2.5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T06:10:40Z",
          "losses": 11,
          "model": "xiaomi/mimo-v2.5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-9077f1e8e006290b",
          "rated_matches": 74,
          "raw_elo_rating": 1502.3343523013145,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "repaired",
          "score": 27.437307852969795,
          "uncertainty": 13.985026918962571,
          "unilateral_faults": 0,
          "wins": 3
        }
      ],
      "GB2-03": [
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 68,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 29,
          "draws": 32,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "xhigh",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-fable-5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-03T17:50:00Z",
          "losses": 7,
          "model": "claude-fable-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-04fa5b762ca703f0",
          "rated_matches": 68,
          "raw_elo_rating": 1699.478327839778,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "xhigh",
          "repair_status": "first_pass",
          "score": 72.45110481946428,
          "uncertainty": 16.4429265428846,
          "unilateral_faults": 0,
          "wins": 29
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 152,
          "capped_draws": 9,
          "coverage_status": "rated",
          "distinct_rated_opponents": 62,
          "draws": 41,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-opus-4-5",
            "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 64,
          "model": "claude-opus-4-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-d5810442d7094396",
          "rated_matches": 152,
          "raw_elo_rating": 1439.6013043122741,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "first_pass",
          "score": 39.20269156862466,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 47
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 58,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 25,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "xhigh",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-opus-5",
            "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-25T15:48:00Z",
          "losses": 4,
          "model": "claude-opus-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-38759212c025e8eb",
          "rated_matches": 58,
          "raw_elo_rating": 1905.622869125327,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "xhigh",
          "repair_status": "first_pass",
          "score": 100.0,
          "uncertainty": 21.344455490411935,
          "unilateral_faults": 0,
          "wins": 54
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 58,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 25,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "xhigh",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-opus-5",
            "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-25T15:48:00Z",
          "losses": 5,
          "model": "claude-opus-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-7caa6c5081d57676",
          "rated_matches": 58,
          "raw_elo_rating": 1886.8165664948144,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "xhigh",
          "repair_status": "first_pass",
          "score": 97.43801622533607,
          "uncertainty": 21.344455490411935,
          "unilateral_faults": 0,
          "wins": 53
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 80,
          "capped_draws": 2,
          "coverage_status": "rated",
          "distinct_rated_opponents": 36,
          "draws": 37,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "xhigh",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-sonnet-5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_7fad32_to_brackets_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-19T15:25:00Z",
          "losses": 16,
          "model": "claude-sonnet-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-1c251b669239429c",
          "rated_matches": 80,
          "raw_elo_rating": 1606.464063932883,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_7fad32_to_brackets_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "xhigh",
          "repair_status": "first_pass",
          "score": 60.285165343979514,
          "uncertainty": 11.805555555555554,
          "unilateral_faults": 0,
          "wins": 27
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 60,
          "capped_draws": 2,
          "coverage_status": "rated",
          "distinct_rated_opponents": 29,
          "draws": 19,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "xhigh",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-sonnet-5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-03T16:50:00Z",
          "losses": 38,
          "model": "claude-sonnet-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-2e43b0d163a7f12d",
          "rated_matches": 60,
          "raw_elo_rating": 1285.3975984985518,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "xhigh",
          "repair_status": "first_pass",
          "score": 15.623941414360715,
          "uncertainty": 20.268439966447993,
          "unilateral_faults": 0,
          "wins": 3
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 88,
          "capped_draws": 1,
          "coverage_status": "rated",
          "distinct_rated_opponents": 42,
          "draws": 42,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "xhigh",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-sonnet-5",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 20,
          "model": "claude-sonnet-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-7dde7ed705ef7793",
          "rated_matches": 88,
          "raw_elo_rating": 1575.6075710349296,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "xhigh",
          "repair_status": "first_pass",
          "score": 56.36010974706571,
          "uncertainty": 9.249894000318006,
          "unilateral_faults": 0,
          "wins": 26
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 192,
          "capped_draws": 6,
          "coverage_status": "rated",
          "distinct_rated_opponents": 72,
          "draws": 67,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "xhigh",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-sonnet-5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_7fad32_to_brackets_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-19T15:25:00Z",
          "losses": 53,
          "model": "claude-sonnet-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-d49e8df479ed0377",
          "rated_matches": 192,
          "raw_elo_rating": 1551.8171700743583,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_7fad32_to_brackets_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "xhigh",
          "repair_status": "first_pass",
          "score": 54.97286325089087,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 72
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 78,
          "capped_draws": 2,
          "coverage_status": "rated",
          "distinct_rated_opponents": 37,
          "draws": 56,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "google/gemini-3.5-flash",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 12,
          "model": "google/gemini-3.5-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-46c3bb79de67d970",
          "rated_matches": 78,
          "raw_elo_rating": 1511.688890303186,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "repaired",
          "score": 47.29777519993979,
          "uncertainty": 12.5043950463012,
          "unilateral_faults": 0,
          "wins": 10
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 140,
          "capped_draws": 4,
          "coverage_status": "rated",
          "distinct_rated_opponents": 48,
          "draws": 23,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "google/gemini-3.5-flash-lite",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 43,
          "model": "google/gemini-3.5-flash-lite",
          "point_rating_method": "sequential_elo",
          "public_id": "E-7ed90f1b43d80cf9",
          "rated_matches": 140,
          "raw_elo_rating": 1664.0889019495849,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "first_pass",
          "score": 69.60101368993861,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 74
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 124,
          "capped_draws": 4,
          "coverage_status": "rated",
          "distinct_rated_opponents": 49,
          "draws": 38,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "google/gemini-3.5-flash-lite",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 52,
          "model": "google/gemini-3.5-flash-lite",
          "point_rating_method": "sequential_elo",
          "public_id": "E-d485651284072880",
          "rated_matches": 124,
          "raw_elo_rating": 1423.3161616673915,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "first_pass",
          "score": 36.51566980579563,
          "uncertainty": 0.9713595499957961,
          "unilateral_faults": 0,
          "wins": 34
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 122,
          "capped_draws": 1,
          "coverage_status": "rated",
          "distinct_rated_opponents": 50,
          "draws": 11,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "google/gemini-3.6-flash",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 23,
          "model": "google/gemini-3.6-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-97580ecf1bd06d40",
          "rated_matches": 122,
          "raw_elo_rating": 1772.0196909880037,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "first_pass",
          "score": 83.98010770719294,
          "uncertainty": 1.3334817333716131,
          "unilateral_faults": 0,
          "wins": 88
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 77,
          "capped_draws": 5,
          "coverage_status": "rated",
          "distinct_rated_opponents": 34,
          "draws": 29,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 30,
          "model": "gpt-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-cc568b7069d5a0fd",
          "rated_matches": 76,
          "raw_elo_rating": 1455.2318976814317,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "first_pass",
          "score": 39.527524812029206,
          "uncertainty": 13.230288229818967,
          "unilateral_faults": 1,
          "wins": 17
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 95,
          "capped_draws": 4,
          "coverage_status": "rated",
          "distinct_rated_opponents": 42,
          "draws": 28,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "xhigh",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.4",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 31,
          "model": "gpt-5.4",
          "point_rating_method": "sequential_elo",
          "public_id": "E-09687fbb17ec9c64",
          "rated_matches": 95,
          "raw_elo_rating": 1439.5396369864504,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "xhigh",
          "repair_status": "first_pass",
          "score": 38.03814073039753,
          "uncertainty": 7.281036307982882,
          "unilateral_faults": 0,
          "wins": 36
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 62,
          "capped_draws": 7,
          "coverage_status": "rated",
          "distinct_rated_opponents": 30,
          "draws": 17,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "xhigh",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.4",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 25,
          "model": "gpt-5.4",
          "point_rating_method": "sequential_elo",
          "public_id": "E-4b75acaf58f14113",
          "rated_matches": 60,
          "raw_elo_rating": 1445.9639269862823,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "xhigh",
          "repair_status": "first_pass",
          "score": 37.49790231061323,
          "uncertainty": 20.268439966447993,
          "unilateral_faults": 2,
          "wins": 18
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 83,
          "capped_draws": 3,
          "coverage_status": "rated",
          "distinct_rated_opponents": 39,
          "draws": 30,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "xhigh",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 29,
          "model": "gpt-5.5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-e53a932f820d9724",
          "rated_matches": 82,
          "raw_elo_rating": 1529.349657382233,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "xhigh",
          "repair_status": "first_pass",
          "score": 49.85325759783324,
          "uncertainty": 11.132129994845172,
          "unilateral_faults": 0,
          "wins": 23
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 90,
          "capped_draws": 2,
          "coverage_status": "rated",
          "distinct_rated_opponents": 43,
          "draws": 39,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "xhigh",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.6-luna",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 32,
          "model": "gpt-5.6-luna",
          "point_rating_method": "sequential_elo",
          "public_id": "E-0fbc2c4195016fbe",
          "rated_matches": 90,
          "raw_elo_rating": 1472.744367648308,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "xhigh",
          "repair_status": "first_pass",
          "score": 42.41087590952312,
          "uncertainty": 8.664241836095918,
          "unilateral_faults": 0,
          "wins": 19
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 68,
          "capped_draws": 2,
          "coverage_status": "rated",
          "distinct_rated_opponents": 32,
          "draws": 27,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "xhigh",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.6-luna",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-10T10:07:13Z",
          "losses": 31,
          "model": "gpt-5.6-luna",
          "point_rating_method": "sequential_elo",
          "public_id": "E-3bca3b4e02f2acf9",
          "rated_matches": 68,
          "raw_elo_rating": 1366.0934547211268,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "xhigh",
          "repair_status": "first_pass",
          "score": 27.034062861276098,
          "uncertainty": 16.4429265428846,
          "unilateral_faults": 0,
          "wins": 10
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 70,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 30,
          "draws": 7,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "xhigh",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.6-sol",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-10T05:30:29Z",
          "losses": 26,
          "model": "gpt-5.6-sol",
          "point_rating_method": "sequential_elo",
          "public_id": "E-2ac4e83a1b9ba989",
          "rated_matches": 70,
          "raw_elo_rating": 1625.9039362576423,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "xhigh",
          "repair_status": "first_pass",
          "score": 62.521116224377955,
          "uncertainty": 15.58908290969266,
          "unilateral_faults": 0,
          "wins": 37
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 92,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 42,
          "draws": 1,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "xhigh",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.6-sol",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 6,
          "model": "gpt-5.6-sol",
          "point_rating_method": "sequential_elo",
          "public_id": "E-d2ec4e4765cdd61a",
          "rated_matches": 92,
          "raw_elo_rating": 1868.3709719929363,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "xhigh",
          "repair_status": "first_pass",
          "score": 96.368869361455,
          "uncertainty": 8.09758473652126,
          "unilateral_faults": 0,
          "wins": 85
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 62,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 29,
          "draws": 15,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "xhigh",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.6-terra",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-10T05:30:29Z",
          "losses": 16,
          "model": "gpt-5.6-terra",
          "point_rating_method": "sequential_elo",
          "public_id": "E-39e763b7d49209b4",
          "rated_matches": 62,
          "raw_elo_rating": 1614.760774095997,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "xhigh",
          "repair_status": "repaired",
          "score": 60.60474629403735,
          "uncertainty": 19.244078834871203,
          "unilateral_faults": 0,
          "wins": 31
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 92,
          "capped_draws": 6,
          "coverage_status": "rated",
          "distinct_rated_opponents": 42,
          "draws": 15,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "xhigh",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "meta/muse-spark-1.2",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-08-13T16:58:34Z",
          "losses": 34,
          "model": "meta/muse-spark-1.2",
          "point_rating_method": "sequential_elo",
          "public_id": "E-967e1c4101f2c062",
          "rated_matches": 92,
          "raw_elo_rating": 1518.9551554503532,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "xhigh",
          "repair_status": "first_pass",
          "score": 48.767930985582225,
          "uncertainty": 8.09758473652126,
          "unilateral_faults": 0,
          "wins": 43
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 120,
          "capped_draws": 4,
          "coverage_status": "rated",
          "distinct_rated_opponents": 48,
          "draws": 57,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "max",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "moonshotai/kimi-k3",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T14:00:00Z",
          "losses": 35,
          "model": "moonshotai/kimi-k3",
          "point_rating_method": "sequential_elo",
          "public_id": "E-8f139a9e4d538859",
          "rated_matches": 120,
          "raw_elo_rating": 1438.701374575963,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "max",
          "repair_status": "first_pass",
          "score": 38.53169274626354,
          "uncertainty": 1.7045454545454586,
          "unilateral_faults": 0,
          "wins": 28
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 136,
          "capped_draws": 1,
          "coverage_status": "rated",
          "distinct_rated_opponents": 47,
          "draws": 49,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "o3",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-03T16:00:00Z",
          "losses": 55,
          "model": "o3",
          "point_rating_method": "sequential_elo",
          "public_id": "E-9f7b8b1adc2ddba7",
          "rated_matches": 134,
          "raw_elo_rating": 1439.0846957731926,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "first_pass",
          "score": 38.84780628544275,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 30
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 17,
          "capped_draws": 0,
          "coverage_status": "under_covered",
          "distinct_rated_opponents": 9,
          "draws": 1,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "xhigh",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "qwen/qwen3.8-max",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 7,
          "model": "qwen/qwen3.8-max",
          "point_rating_method": "sequential_elo",
          "public_id": "E-d2322903ed52a2c3",
          "rated_matches": 17,
          "raw_elo_rating": 1520.0917022516862,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "xhigh",
          "repair_status": "first_pass",
          "score": 41.72942915084835,
          "uncertainty": 74.10113019775793,
          "unilateral_faults": 0,
          "wins": 9
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 0,
          "capped_draws": 0,
          "coverage_status": "pending",
          "distinct_rated_opponents": 0,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "max",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "stealth/ox-alpha",
            "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-08-21T22:22:23Z",
          "losses": 0,
          "model": "stealth/ox-alpha",
          "point_rating_method": "sequential_elo",
          "public_id": "E-41517f1495980c1f",
          "rated_matches": 0,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "max",
          "repair_status": "first_pass",
          "unilateral_faults": 0,
          "wins": 0
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 15,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 6,
          "draws": 3,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "max",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "stealth/ox-alpha",
            "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-08-22T00:27:26Z",
          "losses": 4,
          "model": "stealth/ox-alpha",
          "point_rating_method": "sequential_elo",
          "public_id": "E-463b747dfc9e53e2",
          "rated_matches": 11,
          "raw_elo_rating": 1500.5302324598551,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "max",
          "repair_status": "first_pass",
          "score": 36.177969730843834,
          "uncertainty": 100.0,
          "unilateral_faults": 4,
          "wins": 4
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 12,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 6,
          "draws": 7,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "max",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "stealth/ox-alpha",
            "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-08-22T00:27:26Z",
          "losses": 2,
          "model": "stealth/ox-alpha",
          "point_rating_method": "sequential_elo",
          "public_id": "E-82c718cb6269d828",
          "rated_matches": 12,
          "raw_elo_rating": 1516.6704005400268,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "max",
          "repair_status": "repaired",
          "score": 38.993869999393986,
          "uncertainty": 94.92504905630729,
          "unilateral_faults": 0,
          "wins": 3
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 0,
          "capped_draws": 0,
          "coverage_status": "pending",
          "distinct_rated_opponents": 0,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "max",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "stealth/ox-alpha",
            "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-08-21T22:22:23Z",
          "losses": 0,
          "model": "stealth/ox-alpha",
          "point_rating_method": "sequential_elo",
          "public_id": "E-88583455f6e29fdd",
          "rated_matches": 0,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "max",
          "repair_status": "first_pass",
          "unilateral_faults": 0,
          "wins": 0
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 12,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 6,
          "draws": 8,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "max",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "stealth/ox-alpha",
            "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-08-22T00:27:26Z",
          "losses": 2,
          "model": "stealth/ox-alpha",
          "point_rating_method": "sequential_elo",
          "public_id": "E-de081f655675d088",
          "rated_matches": 12,
          "raw_elo_rating": 1507.5215580197994,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "max",
          "repair_status": "first_pass",
          "score": 37.74752261499379,
          "uncertainty": 94.92504905630729,
          "unilateral_faults": 0,
          "wins": 2
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 124,
          "capped_draws": 6,
          "coverage_status": "rated",
          "distinct_rated_opponents": 48,
          "draws": 50,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "max",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "thinkingmachines/inkling",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 41,
          "model": "thinkingmachines/inkling",
          "point_rating_method": "sequential_elo",
          "public_id": "E-f9259c1ced4fba75",
          "rated_matches": 124,
          "raw_elo_rating": 1455.6626650012568,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "max",
          "repair_status": "first_pass",
          "score": 40.92223596271898,
          "uncertainty": 0.9713595499957961,
          "unilateral_faults": 0,
          "wins": 33
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 18,
          "capped_draws": 1,
          "coverage_status": "under_covered",
          "distinct_rated_opponents": 8,
          "draws": 4,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "max",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "thinkingmachines/inkling-small",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 5,
          "model": "thinkingmachines/inkling-small",
          "point_rating_method": "sequential_elo",
          "public_id": "E-5ee731d79dc75fa4",
          "rated_matches": 18,
          "raw_elo_rating": 1545.532411443232,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "max",
          "repair_status": "first_pass",
          "score": 45.53778410260007,
          "uncertainty": 70.95786693528086,
          "unilateral_faults": 0,
          "wins": 9
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 158,
          "capped_draws": 12,
          "coverage_status": "rated",
          "distinct_rated_opponents": 57,
          "draws": 68,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "x-ai/grok-4.5",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T14:00:00Z",
          "losses": 56,
          "model": "x-ai/grok-4.5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-c0c60ca46f3ce498",
          "rated_matches": 158,
          "raw_elo_rating": 1453.345041387723,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "first_pass",
          "score": 41.15892215398935,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 34
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 124,
          "capped_draws": 8,
          "coverage_status": "rated",
          "distinct_rated_opponents": 43,
          "draws": 30,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "xhigh",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "z-ai/glm-5.2",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_7fad32_to_brackets_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-19T14:50:00Z",
          "losses": 46,
          "model": "z-ai/glm-5.2",
          "point_rating_method": "sequential_elo",
          "public_id": "E-d047860be3ae0d90",
          "rated_matches": 124,
          "raw_elo_rating": 1485.5276957474089,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_7fad32_to_brackets_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "xhigh",
          "repair_status": "first_pass",
          "score": 44.9907509549929,
          "uncertainty": 0.9713595499957961,
          "unilateral_faults": 0,
          "wins": 48
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 120,
          "capped_draws": 10,
          "coverage_status": "rated",
          "distinct_rated_opponents": 43,
          "draws": 50,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "xhigh",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "z-ai/glm-5.2",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_7fad32_to_brackets_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-19T14:50:00Z",
          "losses": 23,
          "model": "z-ai/glm-5.2",
          "point_rating_method": "sequential_elo",
          "public_id": "E-d3a5bd501d8146e0",
          "rated_matches": 120,
          "raw_elo_rating": 1584.6737299429365,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_7fad32_to_brackets_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "xhigh",
          "repair_status": "first_pass",
          "score": 58.417515778425866,
          "uncertainty": 1.7045454545454586,
          "unilateral_faults": 0,
          "wins": 47
        }
      ],
      "GB2-04": [
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 102,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 43,
          "draws": 19,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "xhigh",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-fable-5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-03T17:50:00Z",
          "losses": 5,
          "model": "claude-fable-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-0ca15b39b465b370",
          "rated_matches": 102,
          "raw_elo_rating": 1871.3393976382893,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "xhigh",
          "repair_status": "first_pass",
          "score": 100.0,
          "uncertainty": 5.516463908214657,
          "unilateral_faults": 0,
          "wins": 78
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 0,
          "capped_draws": 0,
          "coverage_status": "pending",
          "distinct_rated_opponents": 0,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "legacy_shared_thinking_budget",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-opus-4-5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "budget",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 0,
          "model": "claude-opus-4-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-e3449ff084425b16",
          "rated_matches": 0,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "budget",
          "reasoning_setting": "legacy_shared_thinking_budget",
          "repair_status": "first_pass",
          "unilateral_faults": 0,
          "wins": 0
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 159,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 60,
          "draws": 83,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-opus-4-5",
            "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 59,
          "model": "claude-opus-4-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-f40463f635c43598",
          "rated_matches": 159,
          "raw_elo_rating": 1441.887567292159,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "first_pass",
          "score": 35.688547830022806,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 17
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 98,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 42,
          "draws": 37,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "xhigh",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-opus-4-8",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-03T17:20:00Z",
          "losses": 17,
          "model": "claude-opus-4-8",
          "point_rating_method": "sequential_elo",
          "public_id": "E-6344242dae68be1b",
          "rated_matches": 98,
          "raw_elo_rating": 1645.9101696696405,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "xhigh",
          "repair_status": "first_pass",
          "score": 65.49748409048952,
          "uncertainty": 6.501890762960602,
          "unilateral_faults": 0,
          "wins": 44
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 80,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 34,
          "draws": 11,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "xhigh",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-opus-5",
            "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-25T15:48:00Z",
          "losses": 13,
          "model": "claude-opus-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-4c98514bdb0eaf10",
          "rated_matches": 80,
          "raw_elo_rating": 1701.9517462530455,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "xhigh",
          "repair_status": "first_pass",
          "score": 73.3977703895628,
          "uncertainty": 11.805555555555554,
          "unilateral_faults": 0,
          "wins": 56
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 84,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 34,
          "draws": 15,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "xhigh",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-opus-5",
            "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-25T15:48:00Z",
          "losses": 6,
          "model": "claude-opus-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-a02883202d334eec",
          "rated_matches": 84,
          "raw_elo_rating": 1837.781141967729,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "xhigh",
          "repair_status": "first_pass",
          "score": 94.27577617470841,
          "uncertainty": 10.482614454664043,
          "unilateral_faults": 0,
          "wins": 63
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 74,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 36,
          "draws": 40,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "xhigh",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-sonnet-5",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 8,
          "model": "claude-sonnet-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-74d5848169176ddd",
          "rated_matches": 74,
          "raw_elo_rating": 1602.2107727942875,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "xhigh",
          "repair_status": "first_pass",
          "score": 57.919430982158175,
          "uncertainty": 13.985026918962571,
          "unilateral_faults": 0,
          "wins": 26
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 86,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 41,
          "draws": 54,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "xhigh",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-sonnet-5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-03T16:50:00Z",
          "losses": 16,
          "model": "claude-sonnet-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-8e980ad934b3251e",
          "rated_matches": 86,
          "raw_elo_rating": 1534.9415708206361,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "xhigh",
          "repair_status": "first_pass",
          "score": 48.16343828710374,
          "uncertainty": 9.855626741889738,
          "unilateral_faults": 0,
          "wins": 16
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 88,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 44,
          "draws": 54,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "xhigh",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "deepseek/deepseek-v4-pro",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 25,
          "model": "deepseek/deepseek-v4-pro",
          "point_rating_method": "sequential_elo",
          "public_id": "E-38bc194a470fbf62",
          "rated_matches": 88,
          "raw_elo_rating": 1457.4828868208863,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "xhigh",
          "repair_status": "repaired",
          "score": 36.42341278591467,
          "uncertainty": 9.249894000318006,
          "unilateral_faults": 0,
          "wins": 9
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 90,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 41,
          "draws": 64,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "google/gemini-3.1-flash-lite",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 20,
          "model": "google/gemini-3.1-flash-lite",
          "point_rating_method": "sequential_elo",
          "public_id": "E-2be6f5c895691cb3",
          "rated_matches": 90,
          "raw_elo_rating": 1486.643674866353,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "repaired",
          "score": 40.94245051776638,
          "uncertainty": 8.664241836095918,
          "unilateral_faults": 0,
          "wins": 6
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 90,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 42,
          "draws": 30,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "google/gemini-3.5-flash",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 38,
          "model": "google/gemini-3.5-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-8e95359e4cbd1851",
          "rated_matches": 90,
          "raw_elo_rating": 1437.4852159713996,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "repaired",
          "score": 33.44484317358223,
          "uncertainty": 8.664241836095918,
          "unilateral_faults": 0,
          "wins": 22
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 137,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 53,
          "draws": 94,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "google/gemini-3.5-flash-lite",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 32,
          "model": "google/gemini-3.5-flash-lite",
          "point_rating_method": "sequential_elo",
          "public_id": "E-39ebef34ae0ea1cb",
          "rated_matches": 136,
          "raw_elo_rating": 1442.4005503966425,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "first_pass",
          "score": 35.37763039440814,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 10
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 136,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 54,
          "draws": 77,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "google/gemini-3.5-flash-lite",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 34,
          "model": "google/gemini-3.5-flash-lite",
          "point_rating_method": "sequential_elo",
          "public_id": "E-953992515ec1424d",
          "rated_matches": 136,
          "raw_elo_rating": 1452.9700185332474,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "first_pass",
          "score": 36.98967690087958,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 25
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 146,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 55,
          "draws": 38,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "google/gemini-3.6-flash",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 63,
          "model": "google/gemini-3.6-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-a5a73c81dfcf4540",
          "rated_matches": 146,
          "raw_elo_rating": 1481.334460302086,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "first_pass",
          "score": 41.49620719860437,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 45
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 159,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 60,
          "draws": 39,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "google/gemini-3.6-flash",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 27,
          "model": "google/gemini-3.6-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-ccfb6c993d1622b0",
          "rated_matches": 156,
          "raw_elo_rating": 1709.790009047594,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "repaired",
          "score": 76.50294353268006,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 90
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 94,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 46,
          "draws": 68,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 19,
          "model": "gpt-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-7e3da77777a95e31",
          "rated_matches": 94,
          "raw_elo_rating": 1475.7924746051574,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "repaired",
          "score": 39.423521122325184,
          "uncertainty": 7.54891760425771,
          "unilateral_faults": 0,
          "wins": 7
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 85,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 37,
          "draws": 43,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "xhigh",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.4",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 4,
          "model": "gpt-5.4",
          "point_rating_method": "sequential_elo",
          "public_id": "E-8d6c86dd58efc4be",
          "rated_matches": 82,
          "raw_elo_rating": 1602.7644735229496,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "xhigh",
          "repair_status": "first_pass",
          "score": 58.3519781342059,
          "uncertainty": 11.132129994845172,
          "unilateral_faults": 0,
          "wins": 35
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 96,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 43,
          "draws": 36,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "xhigh",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.4",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 24,
          "model": "gpt-5.4",
          "point_rating_method": "sequential_elo",
          "public_id": "E-9279285adff8ed29",
          "rated_matches": 96,
          "raw_elo_rating": 1637.1951751819909,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "xhigh",
          "repair_status": "first_pass",
          "score": 64.10539152692174,
          "uncertainty": 7.017308256680951,
          "unilateral_faults": 0,
          "wins": 36
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 86,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 42,
          "draws": 45,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "xhigh",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 35,
          "model": "gpt-5.5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-64bf5daf186f8119",
          "rated_matches": 86,
          "raw_elo_rating": 1398.6125264834243,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "xhigh",
          "repair_status": "first_pass",
          "score": 27.370645611635616,
          "uncertainty": 9.855626741889738,
          "unilateral_faults": 0,
          "wins": 6
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 78,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 36,
          "draws": 44,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "xhigh",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.6-luna",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 23,
          "model": "gpt-5.6-luna",
          "point_rating_method": "sequential_elo",
          "public_id": "E-0a9286b0c21ae9be",
          "rated_matches": 78,
          "raw_elo_rating": 1418.4061831629094,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "xhigh",
          "repair_status": "first_pass",
          "score": 30.06636734322581,
          "uncertainty": 12.5043950463012,
          "unilateral_faults": 0,
          "wins": 11
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 86,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 42,
          "draws": 44,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "xhigh",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.6-luna",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-10T05:30:29Z",
          "losses": 25,
          "model": "gpt-5.6-luna",
          "point_rating_method": "sequential_elo",
          "public_id": "E-e348813cda8b38b7",
          "rated_matches": 86,
          "raw_elo_rating": 1491.9345388012882,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "xhigh",
          "repair_status": "first_pass",
          "score": 41.6040414636828,
          "uncertainty": 9.855626741889738,
          "unilateral_faults": 0,
          "wins": 17
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 98,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 44,
          "draws": 44,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "xhigh",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.6-sol",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-10T05:30:29Z",
          "losses": 6,
          "model": "gpt-5.6-sol",
          "point_rating_method": "sequential_elo",
          "public_id": "E-270a233119b6cc62",
          "rated_matches": 98,
          "raw_elo_rating": 1661.9721859570288,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "xhigh",
          "repair_status": "first_pass",
          "score": 67.94724948155005,
          "uncertainty": 6.501890762960602,
          "unilateral_faults": 0,
          "wins": 48
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 78,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 36,
          "draws": 8,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "xhigh",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.6-sol",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 2,
          "model": "gpt-5.6-sol",
          "point_rating_method": "sequential_elo",
          "public_id": "E-6b542c5d0dcf2279",
          "rated_matches": 78,
          "raw_elo_rating": 1810.5520082026756,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "xhigh",
          "repair_status": "first_pass",
          "score": 89.87612305774321,
          "uncertainty": 12.5043950463012,
          "unilateral_faults": 0,
          "wins": 68
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 94,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 44,
          "draws": 44,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "xhigh",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.6-terra",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-10T05:30:29Z",
          "losses": 18,
          "model": "gpt-5.6-terra",
          "point_rating_method": "sequential_elo",
          "public_id": "E-b85c80e7475ef9ec",
          "rated_matches": 94,
          "raw_elo_rating": 1568.1292217619282,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "xhigh",
          "repair_status": "first_pass",
          "score": 53.506645149871794,
          "uncertainty": 7.54891760425771,
          "unilateral_faults": 0,
          "wins": 32
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 152,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 58,
          "draws": 47,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "max",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "moonshotai/kimi-k3",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T14:00:00Z",
          "losses": 19,
          "model": "moonshotai/kimi-k3",
          "point_rating_method": "sequential_elo",
          "public_id": "E-601725df2c678708",
          "rated_matches": 152,
          "raw_elo_rating": 1735.222095654677,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "max",
          "repair_status": "repaired",
          "score": 80.31858860898552,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 86
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 90,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 44,
          "draws": 65,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "nvidia/nemotron-3-ultra-550b-a55b",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-11T17:22:09Z",
          "losses": 19,
          "model": "nvidia/nemotron-3-ultra-550b-a55b",
          "point_rating_method": "sequential_elo",
          "public_id": "E-958dea26b779a042",
          "rated_matches": 90,
          "raw_elo_rating": 1461.9284785190819,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "repaired",
          "score": 37.17290928698389,
          "uncertainty": 8.664241836095918,
          "unilateral_faults": 0,
          "wins": 6
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 80,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 39,
          "draws": 43,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "openai/gpt-oss-120b",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 23,
          "model": "openai/gpt-oss-120b",
          "point_rating_method": "sequential_elo",
          "public_id": "E-3a27113d21c73b01",
          "rated_matches": 80,
          "raw_elo_rating": 1479.2518107556666,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "repaired",
          "score": 39.431761090888465,
          "uncertainty": 11.805555555555554,
          "unilateral_faults": 0,
          "wins": 14
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 20,
          "capped_draws": 0,
          "coverage_status": "under_covered",
          "distinct_rated_opponents": 11,
          "draws": 10,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "xhigh",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "qwen/qwen3.8-max",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-08-18T17:01:47Z",
          "losses": 1,
          "model": "qwen/qwen3.8-max",
          "point_rating_method": "sequential_elo",
          "public_id": "E-2c5709bd26aef5e5",
          "rated_matches": 20,
          "raw_elo_rating": 1594.1909851365033,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "xhigh",
          "repair_status": "first_pass",
          "score": 50.427853739274326,
          "uncertainty": 65.3589451179962,
          "unilateral_faults": 0,
          "wins": 9
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 16,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 8,
          "draws": 2,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "max",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "stealth/ox-alpha",
            "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-08-22T00:27:26Z",
          "losses": 0,
          "model": "stealth/ox-alpha",
          "point_rating_method": "sequential_elo",
          "public_id": "E-454f79b70ee12fe0",
          "rated_matches": 16,
          "raw_elo_rating": 1660.6322344500543,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "max",
          "repair_status": "first_pass",
          "score": 59.07784964141441,
          "uncertainty": 77.5178125181665,
          "unilateral_faults": 0,
          "wins": 14
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 16,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 8,
          "draws": 7,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "max",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "stealth/ox-alpha",
            "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-08-22T00:27:26Z",
          "losses": 5,
          "model": "stealth/ox-alpha",
          "point_rating_method": "sequential_elo",
          "public_id": "E-6a2b79a57d322dae",
          "rated_matches": 16,
          "raw_elo_rating": 1484.413760171134,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "max",
          "repair_status": "first_pass",
          "score": 32.20115422348307,
          "uncertainty": 77.5178125181665,
          "unilateral_faults": 0,
          "wins": 4
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 16,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 8,
          "draws": 8,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "max",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "stealth/ox-alpha",
            "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-08-22T00:27:26Z",
          "losses": 4,
          "model": "stealth/ox-alpha",
          "point_rating_method": "sequential_elo",
          "public_id": "E-d89754cdf98b2ae2",
          "rated_matches": 16,
          "raw_elo_rating": 1496.1444853273942,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "max",
          "repair_status": "first_pass",
          "score": 33.990314686632,
          "uncertainty": 77.5178125181665,
          "unilateral_faults": 0,
          "wins": 4
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 86,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 42,
          "draws": 60,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "tencent/hy3-preview",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 19,
          "model": "tencent/hy3-preview",
          "point_rating_method": "sequential_elo",
          "public_id": "E-51c104b34ef2a244",
          "rated_matches": 86,
          "raw_elo_rating": 1428.305372108474,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "first_pass",
          "score": 31.89937377831447,
          "uncertainty": 9.855626741889738,
          "unilateral_faults": 0,
          "wins": 7
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 134,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 53,
          "draws": 84,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "max",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "thinkingmachines/inkling",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 22,
          "model": "thinkingmachines/inkling",
          "point_rating_method": "sequential_elo",
          "public_id": "E-f130161523da1e6b",
          "rated_matches": 134,
          "raw_elo_rating": 1476.2686847664681,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "max",
          "repair_status": "first_pass",
          "score": 40.504702920191605,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 28
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 17,
          "capped_draws": 0,
          "coverage_status": "under_covered",
          "distinct_rated_opponents": 8,
          "draws": 9,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "max",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "thinkingmachines/inkling-small",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-08-18T19:36:24Z",
          "losses": 1,
          "model": "thinkingmachines/inkling-small",
          "point_rating_method": "sequential_elo",
          "public_id": "E-df6d76539ff35338",
          "rated_matches": 17,
          "raw_elo_rating": 1562.2633173996858,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "max",
          "repair_status": "repaired",
          "score": 44.49159171005959,
          "uncertainty": 74.10113019775793,
          "unilateral_faults": 0,
          "wins": 7
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 154,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 59,
          "draws": 64,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "x-ai/grok-4.5",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T14:00:00Z",
          "losses": 54,
          "model": "x-ai/grok-4.5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-07caaa12175b0b3c",
          "rated_matches": 154,
          "raw_elo_rating": 1419.3352985192469,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "first_pass",
          "score": 32.171720342982304,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 36
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 68,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 34,
          "draws": 52,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "xiaomi/mimo-v2.5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T06:10:40Z",
          "losses": 10,
          "model": "xiaomi/mimo-v2.5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-f8929b12716a2221",
          "rated_matches": 68,
          "raw_elo_rating": 1490.8209858823616,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "repaired",
          "score": 40.63045169882911,
          "uncertainty": 16.4429265428846,
          "unilateral_faults": 0,
          "wins": 6
        }
      ],
      "GB2-05": [
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 100,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 43,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "xhigh",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-fable-5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 16,
          "model": "claude-fable-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-5aa4402ccce7b855",
          "rated_matches": 100,
          "raw_elo_rating": 2023.8636251018338,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "xhigh",
          "repair_status": "repaired",
          "score": 91.20233840190105,
          "uncertainty": 6.001859510499461,
          "unilateral_faults": 0,
          "wins": 84
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 0,
          "capped_draws": 0,
          "coverage_status": "pending",
          "distinct_rated_opponents": 0,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "legacy_shared_thinking_budget",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-opus-4-5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "budget",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 0,
          "model": "claude-opus-4-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-7e9bc3ebc12ef500",
          "rated_matches": 0,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "budget",
          "reasoning_setting": "legacy_shared_thinking_budget",
          "repair_status": "first_pass",
          "unilateral_faults": 0,
          "wins": 0
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 200,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 67,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-opus-4-5",
            "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 86,
          "model": "claude-opus-4-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-ccacc93776fb7c88",
          "rated_matches": 200,
          "raw_elo_rating": 1510.738619126404,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "first_pass",
          "score": 49.55470457849347,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 114
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 120,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 60,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "xhigh",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-opus-4-8",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 65,
          "model": "claude-opus-4-8",
          "point_rating_method": "sequential_elo",
          "public_id": "E-6774d700e60de31a",
          "rated_matches": 120,
          "raw_elo_rating": 1536.317407962045,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "xhigh",
          "repair_status": "repaired",
          "score": 51.00200589427959,
          "uncertainty": 1.7045454545454586,
          "unilateral_faults": 0,
          "wins": 55
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 70,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 29,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "xhigh",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-opus-5",
            "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-25T10:50:00Z",
          "losses": 0,
          "model": "claude-opus-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-3f3686d02d1503fa",
          "rated_matches": 70,
          "raw_elo_rating": 2137.478337961861,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "xhigh",
          "repair_status": "first_pass",
          "score": 100.0,
          "uncertainty": 15.58908290969266,
          "unilateral_faults": 0,
          "wins": 70
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 70,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 31,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "xhigh",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-opus-5",
            "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-25T10:50:00Z",
          "losses": 22,
          "model": "claude-opus-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-a35dfc1adc62e4eb",
          "rated_matches": 70,
          "raw_elo_rating": 1814.876197516069,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "xhigh",
          "repair_status": "first_pass",
          "score": 73.21113571418141,
          "uncertainty": 15.58908290969266,
          "unilateral_faults": 0,
          "wins": 48
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 94,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 45,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "xhigh",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-sonnet-5",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 39,
          "model": "claude-sonnet-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-750cee28d20157cb",
          "rated_matches": 94,
          "raw_elo_rating": 1522.3810009155313,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "xhigh",
          "repair_status": "first_pass",
          "score": 49.4564743296236,
          "uncertainty": 7.54891760425771,
          "unilateral_faults": 0,
          "wins": 55
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 102,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 48,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "xhigh",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-sonnet-5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-03T16:50:00Z",
          "losses": 53,
          "model": "claude-sonnet-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-c902807aab849f31",
          "rated_matches": 102,
          "raw_elo_rating": 1584.3884545773712,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "xhigh",
          "repair_status": "first_pass",
          "score": 54.74058980227671,
          "uncertainty": 5.516463908214657,
          "unilateral_faults": 0,
          "wins": 49
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 102,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 49,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "xhigh",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "deepseek/deepseek-v4-flash",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 48,
          "model": "deepseek/deepseek-v4-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-b3d889b0631db85f",
          "rated_matches": 102,
          "raw_elo_rating": 1549.0224155741603,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "xhigh",
          "repair_status": "repaired",
          "score": 51.803795837193945,
          "uncertainty": 5.516463908214657,
          "unilateral_faults": 0,
          "wins": 54
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 98,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 45,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "xhigh",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "deepseek/deepseek-v4-pro",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 35,
          "model": "deepseek/deepseek-v4-pro",
          "point_rating_method": "sequential_elo",
          "public_id": "E-0ca4798825ceaccb",
          "rated_matches": 98,
          "raw_elo_rating": 1818.7116137409091,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "xhigh",
          "repair_status": "repaired",
          "score": 74.1333084252556,
          "uncertainty": 6.501890762960602,
          "unilateral_faults": 0,
          "wins": 63
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 88,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 43,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "google/gemini-3.1-flash-lite",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 70,
          "model": "google/gemini-3.1-flash-lite",
          "point_rating_method": "sequential_elo",
          "public_id": "E-a72dd193e1dc4331",
          "rated_matches": 88,
          "raw_elo_rating": 1165.8540579796686,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "repaired",
          "score": 19.73749709047673,
          "uncertainty": 9.249894000318006,
          "unilateral_faults": 0,
          "wins": 18
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 100,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 49,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "google/gemini-3.5-flash",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 55,
          "model": "google/gemini-3.5-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-b50da126631c1ea1",
          "rated_matches": 100,
          "raw_elo_rating": 1552.7470805088597,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "repaired",
          "score": 52.08084603218233,
          "uncertainty": 6.001859510499461,
          "unilateral_faults": 0,
          "wins": 45
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 150,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 52,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "google/gemini-3.5-flash-lite",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 110,
          "model": "google/gemini-3.5-flash-lite",
          "point_rating_method": "sequential_elo",
          "public_id": "E-06abb3c93d2072c8",
          "rated_matches": 150,
          "raw_elo_rating": 1256.6289119553658,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "first_pass",
          "score": 28.093244733221475,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 40
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 150,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 53,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "google/gemini-3.5-flash-lite",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 112,
          "model": "google/gemini-3.5-flash-lite",
          "point_rating_method": "sequential_elo",
          "public_id": "E-5b803013ec40d15d",
          "rated_matches": 150,
          "raw_elo_rating": 1163.2464253090598,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "first_pass",
          "score": 20.338768095269625,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 38
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 146,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 56,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "google/gemini-3.6-flash",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 9,
          "model": "google/gemini-3.6-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-8b9ff59d79afb558",
          "rated_matches": 146,
          "raw_elo_rating": 2021.9160560630553,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "first_pass",
          "score": 91.60611803088719,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 137
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 142,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 55,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "google/gemini-3.6-flash",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 35,
          "model": "google/gemini-3.6-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-c4f143aad203feb3",
          "rated_matches": 142,
          "raw_elo_rating": 1814.6990927676245,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "first_pass",
          "score": 74.3607806821286,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 107
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 102,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 45,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 47,
          "model": "gpt-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-c5ad048b6fb4e93d",
          "rated_matches": 102,
          "raw_elo_rating": 1681.8135849530192,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "first_pass",
          "score": 62.830767356755665,
          "uncertainty": 5.516463908214657,
          "unilateral_faults": 0,
          "wins": 55
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 94,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 44,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "xhigh",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.4",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 1,
          "model": "gpt-5.4",
          "point_rating_method": "sequential_elo",
          "public_id": "E-dcce778d7a3114fa",
          "rated_matches": 94,
          "raw_elo_rating": 1994.8915096393325,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "xhigh",
          "repair_status": "first_pass",
          "score": 88.69372140533535,
          "uncertainty": 7.54891760425771,
          "unilateral_faults": 0,
          "wins": 93
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 94,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 43,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "xhigh",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.4",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 8,
          "model": "gpt-5.4",
          "point_rating_method": "sequential_elo",
          "public_id": "E-f6403f7a30e19e82",
          "rated_matches": 94,
          "raw_elo_rating": 2048.0082481553145,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "xhigh",
          "repair_status": "first_pass",
          "score": 93.10453249742434,
          "uncertainty": 7.54891760425771,
          "unilateral_faults": 0,
          "wins": 86
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 98,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 45,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "xhigh",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 21,
          "model": "gpt-5.5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-762e9d80a60b41ed",
          "rated_matches": 98,
          "raw_elo_rating": 1927.4799055461476,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "xhigh",
          "repair_status": "first_pass",
          "score": 83.16542149104123,
          "uncertainty": 6.501890762960602,
          "unilateral_faults": 0,
          "wins": 77
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 108,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 52,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "xhigh",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.6-luna",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-10T05:30:29Z",
          "losses": 57,
          "model": "gpt-5.6-luna",
          "point_rating_method": "sequential_elo",
          "public_id": "E-25a83ddaeb1268a4",
          "rated_matches": 108,
          "raw_elo_rating": 1629.976691086905,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "xhigh",
          "repair_status": "first_pass",
          "score": 58.61758837696586,
          "uncertainty": 4.1413142610575715,
          "unilateral_faults": 0,
          "wins": 51
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 94,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 44,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "xhigh",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.6-luna",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 35,
          "model": "gpt-5.6-luna",
          "point_rating_method": "sequential_elo",
          "public_id": "E-3b8df7a8d128f873",
          "rated_matches": 94,
          "raw_elo_rating": 1585.7142254237854,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "xhigh",
          "repair_status": "first_pass",
          "score": 54.71566186567154,
          "uncertainty": 7.54891760425771,
          "unilateral_faults": 0,
          "wins": 59
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 88,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 43,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "xhigh",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.6-sol",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 23,
          "model": "gpt-5.6-sol",
          "point_rating_method": "sequential_elo",
          "public_id": "E-225037bcf869a775",
          "rated_matches": 88,
          "raw_elo_rating": 1649.8907644291016,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "xhigh",
          "repair_status": "first_pass",
          "score": 59.931879001613865,
          "uncertainty": 9.249894000318006,
          "unilateral_faults": 0,
          "wins": 65
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 94,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 44,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "xhigh",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.6-sol",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-10T05:30:29Z",
          "losses": 34,
          "model": "gpt-5.6-sol",
          "point_rating_method": "sequential_elo",
          "public_id": "E-af9c2c2998294ad0",
          "rated_matches": 94,
          "raw_elo_rating": 1744.4095445478265,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "xhigh",
          "repair_status": "first_pass",
          "score": 67.89371257833555,
          "uncertainty": 7.54891760425771,
          "unilateral_faults": 0,
          "wins": 60
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 98,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 45,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "xhigh",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.6-terra",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-10T05:30:29Z",
          "losses": 42,
          "model": "gpt-5.6-terra",
          "point_rating_method": "sequential_elo",
          "public_id": "E-012ecb9ce0709c05",
          "rated_matches": 98,
          "raw_elo_rating": 1679.100259521219,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "xhigh",
          "repair_status": "repaired",
          "score": 62.53998912556835,
          "uncertainty": 6.501890762960602,
          "unilateral_faults": 0,
          "wins": 56
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 90,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 45,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "mistralai/mistral-medium-3-5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 65,
          "model": "mistralai/mistral-medium-3-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-1954b83d439b455c",
          "rated_matches": 90,
          "raw_elo_rating": 1231.6665190864155,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "repaired",
          "score": 25.241466318726623,
          "uncertainty": 8.664241836095918,
          "unilateral_faults": 0,
          "wins": 25
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 112,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 53,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "nvidia/nemotron-3-ultra-550b-a55b",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 68,
          "model": "nvidia/nemotron-3-ultra-550b-a55b",
          "point_rating_method": "sequential_elo",
          "public_id": "E-48ed5c5e00ef38fb",
          "rated_matches": 112,
          "raw_elo_rating": 1422.3746295977035,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "first_pass",
          "score": 41.43514174030673,
          "uncertainty": 3.286043419179858,
          "unilateral_faults": 0,
          "wins": 44
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 98,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 49,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "nvidia/nemotron-3-ultra-550b-a55b",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-11T17:22:09Z",
          "losses": 54,
          "model": "nvidia/nemotron-3-ultra-550b-a55b",
          "point_rating_method": "sequential_elo",
          "public_id": "E-da3b98638ff53ea9",
          "rated_matches": 98,
          "raw_elo_rating": 1460.5213788610474,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "repaired",
          "score": 44.38921070339174,
          "uncertainty": 6.501890762960602,
          "unilateral_faults": 0,
          "wins": 44
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 159,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 63,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "o3",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 61,
          "model": "o3",
          "point_rating_method": "sequential_elo",
          "public_id": "E-4724b57e861c4ecf",
          "rated_matches": 159,
          "raw_elo_rating": 1655.548273394007,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "first_pass",
          "score": 61.29661124596546,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 98
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 172,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 62,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "o3",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-03T16:00:00Z",
          "losses": 92,
          "model": "o3",
          "point_rating_method": "sequential_elo",
          "public_id": "E-61d05a26a332d2e5",
          "rated_matches": 172,
          "raw_elo_rating": 1474.0668126827427,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "first_pass",
          "score": 46.326990156278704,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 80
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 151,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 55,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "o3",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-03T15:45:00Z",
          "losses": 82,
          "model": "o3",
          "point_rating_method": "sequential_elo",
          "public_id": "E-9bfe5e29476019eb",
          "rated_matches": 151,
          "raw_elo_rating": 1405.0942815728604,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "first_pass",
          "score": 40.430707369140535,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 69
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 152,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 52,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "o3",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-03T15:50:00Z",
          "losses": 57,
          "model": "o3",
          "point_rating_method": "sequential_elo",
          "public_id": "E-ffb183b7ecfe85e0",
          "rated_matches": 152,
          "raw_elo_rating": 1567.5529820460479,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "first_pass",
          "score": 53.93008798138243,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 95
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 22,
          "capped_draws": 0,
          "coverage_status": "under_covered",
          "distinct_rated_opponents": 11,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "xhigh",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "qwen/qwen3.8-max",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 9,
          "model": "qwen/qwen3.8-max",
          "point_rating_method": "sequential_elo",
          "public_id": "E-7cc7204834cbed5f",
          "rated_matches": 22,
          "raw_elo_rating": 1528.9563415565945,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "xhigh",
          "repair_status": "first_pass",
          "score": 46.48436747017905,
          "uncertainty": 60.5072070285374,
          "unilateral_faults": 0,
          "wins": 13
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 16,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 8,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "max",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "stealth/ox-alpha",
            "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-08-22T00:27:26Z",
          "losses": 6,
          "model": "stealth/ox-alpha",
          "point_rating_method": "sequential_elo",
          "public_id": "E-45b32dc2eea8fd55",
          "rated_matches": 16,
          "raw_elo_rating": 1550.9689443760603,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "max",
          "repair_status": "first_pass",
          "score": 47.18224500965281,
          "uncertainty": 77.5178125181665,
          "unilateral_faults": 0,
          "wins": 10
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 16,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 8,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "max",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "stealth/ox-alpha",
            "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-08-22T00:27:26Z",
          "losses": 7,
          "model": "stealth/ox-alpha",
          "point_rating_method": "sequential_elo",
          "public_id": "E-b2ff4a9d0e899fba",
          "rated_matches": 16,
          "raw_elo_rating": 1528.592744862467,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "max",
          "repair_status": "first_pass",
          "score": 45.324126612875546,
          "uncertainty": 77.5178125181665,
          "unilateral_faults": 0,
          "wins": 9
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 16,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 8,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "max",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "stealth/ox-alpha",
            "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-08-22T00:27:26Z",
          "losses": 2,
          "model": "stealth/ox-alpha",
          "point_rating_method": "sequential_elo",
          "public_id": "E-b6ae2b718b132aa0",
          "rated_matches": 16,
          "raw_elo_rating": 1634.7728591293924,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "max",
          "repair_status": "repaired",
          "score": 54.14131755593233,
          "uncertainty": 77.5178125181665,
          "unilateral_faults": 0,
          "wins": 14
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 108,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 52,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "stepfun/step-3.7-flash",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 52,
          "model": "stepfun/step-3.7-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-358338a9fbdbcb6a",
          "rated_matches": 108,
          "raw_elo_rating": 1425.1003871142666,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "repaired",
          "score": 41.604671181441674,
          "uncertainty": 4.1413142610575715,
          "unilateral_faults": 0,
          "wins": 56
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 96,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 46,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "tencent/hy3-preview",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-03T19:10:00Z",
          "losses": 48,
          "model": "tencent/hy3-preview",
          "point_rating_method": "sequential_elo",
          "public_id": "E-92dc0ac61d798488",
          "rated_matches": 96,
          "raw_elo_rating": 1628.3276946126373,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "repaired",
          "score": 58.289597890358415,
          "uncertainty": 7.017308256680951,
          "unilateral_faults": 0,
          "wins": 48
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 154,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 53,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "max",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "thinkingmachines/inkling",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 126,
          "model": "thinkingmachines/inkling",
          "point_rating_method": "sequential_elo",
          "public_id": "E-2c483dc32fc18ba8",
          "rated_matches": 154,
          "raw_elo_rating": 1095.9127049060485,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "max",
          "repair_status": "first_pass",
          "score": 14.782485995492653,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 28
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 166,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 59,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "max",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "thinkingmachines/inkling",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 124,
          "model": "thinkingmachines/inkling",
          "point_rating_method": "sequential_elo",
          "public_id": "E-e9202aa1565d1c4e",
          "rated_matches": 166,
          "raw_elo_rating": 1183.8805167121868,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "max",
          "repair_status": "repaired",
          "score": 22.184970337787764,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 42
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 17,
          "capped_draws": 0,
          "coverage_status": "under_covered",
          "distinct_rated_opponents": 9,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "max",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "thinkingmachines/inkling-small",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 8,
          "model": "thinkingmachines/inkling-small",
          "point_rating_method": "sequential_elo",
          "public_id": "E-e8805bb60afd625c",
          "rated_matches": 17,
          "raw_elo_rating": 1503.5327853795927,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "max",
          "repair_status": "first_pass",
          "score": 43.47012582547535,
          "uncertainty": 74.10113019775793,
          "unilateral_faults": 0,
          "wins": 9
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 142,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 56,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "x-ai/grok-4.5",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T14:00:00Z",
          "losses": 41,
          "model": "x-ai/grok-4.5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-8e6cb252293b2af9",
          "rated_matches": 142,
          "raw_elo_rating": 1780.9418496208198,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "first_pass",
          "score": 71.55758103790589,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 101
        }
      ],
      "GB2-06": [
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 84,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 39,
          "draws": 9,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "xhigh",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-fable-5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 10,
          "model": "claude-fable-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-499fbc92ee0778fb",
          "rated_matches": 84,
          "raw_elo_rating": 1909.8483590250705,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "xhigh",
          "repair_status": "repaired",
          "score": 84.82657150590221,
          "uncertainty": 10.482614454664043,
          "unilateral_faults": 0,
          "wins": 65
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 0,
          "capped_draws": 0,
          "coverage_status": "pending",
          "distinct_rated_opponents": 0,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "legacy_shared_thinking_budget",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-opus-4-5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "budget",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 0,
          "model": "claude-opus-4-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-41f8f2b491917557",
          "rated_matches": 0,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "budget",
          "reasoning_setting": "legacy_shared_thinking_budget",
          "repair_status": "repaired",
          "unilateral_faults": 0,
          "wins": 0
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 178,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 64,
          "draws": 17,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-opus-4-5",
            "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 71,
          "model": "claude-opus-4-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-df9bde92610963b7",
          "rated_matches": 178,
          "raw_elo_rating": 1601.6726322378718,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "first_pass",
          "score": 59.34143229501704,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 90
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 84,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 38,
          "draws": 2,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "xhigh",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-opus-4-8",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-03T17:20:00Z",
          "losses": 18,
          "model": "claude-opus-4-8",
          "point_rating_method": "sequential_elo",
          "public_id": "E-e804041031295d93",
          "rated_matches": 84,
          "raw_elo_rating": 1827.373724966149,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "xhigh",
          "repair_status": "first_pass",
          "score": 77.69399608634865,
          "uncertainty": 10.482614454664043,
          "unilateral_faults": 0,
          "wins": 64
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 96,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 45,
          "draws": 11,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "xhigh",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-sonnet-5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-03T16:50:00Z",
          "losses": 35,
          "model": "claude-sonnet-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-51f3682dc3b76107",
          "rated_matches": 96,
          "raw_elo_rating": 1630.987339864078,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "xhigh",
          "repair_status": "first_pass",
          "score": 60.949848353843976,
          "uncertainty": 7.017308256680951,
          "unilateral_faults": 0,
          "wins": 50
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 92,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 42,
          "draws": 5,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "xhigh",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-sonnet-5",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 64,
          "model": "claude-sonnet-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-c4133ea4f4d4dfb9",
          "rated_matches": 92,
          "raw_elo_rating": 1282.520215691405,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "xhigh",
          "repair_status": "first_pass",
          "score": 30.738957507215925,
          "uncertainty": 8.09758473652126,
          "unilateral_faults": 0,
          "wins": 23
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 86,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 40,
          "draws": 1,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "xhigh",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "deepseek/deepseek-v4-flash",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 61,
          "model": "deepseek/deepseek-v4-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-5f5fd61f4544b8d7",
          "rated_matches": 86,
          "raw_elo_rating": 1269.9135910657938,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "xhigh",
          "repair_status": "first_pass",
          "score": 29.52707950589016,
          "uncertainty": 9.855626741889738,
          "unilateral_faults": 0,
          "wins": 24
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 118,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 58,
          "draws": 2,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "xhigh",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "deepseek/deepseek-v4-pro",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 63,
          "model": "deepseek/deepseek-v4-pro",
          "point_rating_method": "sequential_elo",
          "public_id": "E-c9778645f1bbd12c",
          "rated_matches": 118,
          "raw_elo_rating": 1399.9603695080434,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "xhigh",
          "repair_status": "first_pass",
          "score": 41.31141247367678,
          "uncertainty": 2.084924851410568,
          "unilateral_faults": 0,
          "wins": 53
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 95,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 45,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "google/gemini-3.1-flash-lite",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 66,
          "model": "google/gemini-3.1-flash-lite",
          "point_rating_method": "sequential_elo",
          "public_id": "E-6238c7d8dc9e77d9",
          "rated_matches": 95,
          "raw_elo_rating": 1265.0077154404437,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "repaired",
          "score": 29.280934011909366,
          "uncertainty": 7.281036307982882,
          "unilateral_faults": 0,
          "wins": 29
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 84,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 40,
          "draws": 5,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "google/gemini-3.5-flash",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 17,
          "model": "google/gemini-3.5-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-5dcb27eaa0273049",
          "rated_matches": 84,
          "raw_elo_rating": 1877.810620435143,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "repaired",
          "score": 82.05588219794666,
          "uncertainty": 10.482614454664043,
          "unilateral_faults": 0,
          "wins": 62
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 144,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 51,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "google/gemini-3.5-flash-lite",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 108,
          "model": "google/gemini-3.5-flash-lite",
          "point_rating_method": "sequential_elo",
          "public_id": "E-09a450a1726f909a",
          "rated_matches": 144,
          "raw_elo_rating": 1152.7930953344032,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "first_pass",
          "score": 20.234221204308028,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 36
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 150,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 55,
          "draws": 13,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "google/gemini-3.5-flash-lite",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 44,
          "model": "google/gemini-3.5-flash-lite",
          "point_rating_method": "sequential_elo",
          "public_id": "E-48cc2611d5aa8816",
          "rated_matches": 150,
          "raw_elo_rating": 1719.306434738836,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "repaired",
          "score": 69.28510967031967,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 93
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 164,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 66,
          "draws": 12,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "google/gemini-3.6-flash",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 35,
          "model": "google/gemini-3.6-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-280a7de63c992141",
          "rated_matches": 164,
          "raw_elo_rating": 1864.479412642781,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "repaired",
          "score": 81.96204277453973,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 117
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 150,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 58,
          "draws": 2,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "google/gemini-3.6-flash",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 11,
          "model": "google/gemini-3.6-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-905531e52a8460f5",
          "rated_matches": 150,
          "raw_elo_rating": 2074.465573071347,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "repaired",
          "score": 100.0,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 137
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 90,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 42,
          "draws": 9,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 31,
          "model": "gpt-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-1b082700b3692175",
          "rated_matches": 90,
          "raw_elo_rating": 1690.7719660077682,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "repaired",
          "score": 66.00620122264021,
          "uncertainty": 8.664241836095918,
          "unilateral_faults": 0,
          "wins": 50
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 96,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 43,
          "draws": 3,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "xhigh",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.4",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 6,
          "model": "gpt-5.4",
          "point_rating_method": "sequential_elo",
          "public_id": "E-5032a25edce1eb13",
          "rated_matches": 96,
          "raw_elo_rating": 1948.9952096118298,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "xhigh",
          "repair_status": "first_pass",
          "score": 88.45182081930464,
          "uncertainty": 7.017308256680951,
          "unilateral_faults": 0,
          "wins": 87
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 84,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 39,
          "draws": 10,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "xhigh",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.4",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 7,
          "model": "gpt-5.4",
          "point_rating_method": "sequential_elo",
          "public_id": "E-6e5bbab022d4d9fa",
          "rated_matches": 84,
          "raw_elo_rating": 1963.0028481780307,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "xhigh",
          "repair_status": "repaired",
          "score": 89.42348069013059,
          "uncertainty": 10.482614454664043,
          "unilateral_faults": 0,
          "wins": 67
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 84,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 41,
          "draws": 5,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "xhigh",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 16,
          "model": "gpt-5.5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-4175a77ccf4c269b",
          "rated_matches": 84,
          "raw_elo_rating": 1909.8196476234893,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "xhigh",
          "repair_status": "first_pass",
          "score": 84.82408848503748,
          "uncertainty": 10.482614454664043,
          "unilateral_faults": 0,
          "wins": 63
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 86,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 38,
          "draws": 10,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "xhigh",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.6-luna",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-10T05:30:29Z",
          "losses": 22,
          "model": "gpt-5.6-luna",
          "point_rating_method": "sequential_elo",
          "public_id": "E-9eafeacabdedfdba",
          "rated_matches": 86,
          "raw_elo_rating": 1790.7895280558996,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "xhigh",
          "repair_status": "first_pass",
          "score": 74.57349828912908,
          "uncertainty": 9.855626741889738,
          "unilateral_faults": 0,
          "wins": 54
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 90,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 42,
          "draws": 8,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "xhigh",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.6-luna",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 9,
          "model": "gpt-5.6-luna",
          "point_rating_method": "sequential_elo",
          "public_id": "E-d8cf92ac05965d5e",
          "rated_matches": 89,
          "raw_elo_rating": 1876.2466265033572,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "xhigh",
          "repair_status": "first_pass",
          "score": 82.02633954021168,
          "uncertainty": 8.954627669472988,
          "unilateral_faults": 0,
          "wins": 72
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 86,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 40,
          "draws": 3,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "xhigh",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.6-sol",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-10T05:30:29Z",
          "losses": 23,
          "model": "gpt-5.6-sol",
          "point_rating_method": "sequential_elo",
          "public_id": "E-eb315c759774ef38",
          "rated_matches": 86,
          "raw_elo_rating": 1810.9235349193502,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "xhigh",
          "repair_status": "first_pass",
          "score": 76.31472847571924,
          "uncertainty": 9.855626741889738,
          "unilateral_faults": 0,
          "wins": 60
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 90,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 43,
          "draws": 6,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "xhigh",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.6-sol",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 1,
          "model": "gpt-5.6-sol",
          "point_rating_method": "sequential_elo",
          "public_id": "E-edb238a0d9a72c9f",
          "rated_matches": 90,
          "raw_elo_rating": 1996.2299624147333,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "xhigh",
          "repair_status": "first_pass",
          "score": 92.42283491539342,
          "uncertainty": 8.664241836095918,
          "unilateral_faults": 0,
          "wins": 83
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 92,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 44,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "xhigh",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.6-terra",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-10T05:30:29Z",
          "losses": 34,
          "model": "gpt-5.6-terra",
          "point_rating_method": "sequential_elo",
          "public_id": "E-e6571a10c1120fab",
          "rated_matches": 92,
          "raw_elo_rating": 1762.4255362201798,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "xhigh",
          "repair_status": "first_pass",
          "score": 72.24215339252389,
          "uncertainty": 8.09758473652126,
          "unilateral_faults": 0,
          "wins": 58
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 90,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 44,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "mistralai/mistral-medium-3-5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 62,
          "model": "mistralai/mistral-medium-3-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-6c35f5ff426e7ada",
          "rated_matches": 90,
          "raw_elo_rating": 1253.7221512485582,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "repaired",
          "score": 28.20923732650551,
          "uncertainty": 8.664241836095918,
          "unilateral_faults": 0,
          "wins": 28
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 91,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 46,
          "draws": 7,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "nvidia/nemotron-3-ultra-550b-a55b",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-11T17:22:09Z",
          "losses": 59,
          "model": "nvidia/nemotron-3-ultra-550b-a55b",
          "point_rating_method": "sequential_elo",
          "public_id": "E-ba2fb1c121873708",
          "rated_matches": 91,
          "raw_elo_rating": 1392.9558533954528,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "repaired",
          "score": 40.27021537575938,
          "uncertainty": 8.378603514268699,
          "unilateral_faults": 0,
          "wins": 25
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 150,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 51,
          "draws": 4,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "o3",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-03T16:00:00Z",
          "losses": 64,
          "model": "o3",
          "point_rating_method": "sequential_elo",
          "public_id": "E-2c94ff7a30958259",
          "rated_matches": 150,
          "raw_elo_rating": 1560.59701847636,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "first_pass",
          "score": 55.55959401084185,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 82
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 151,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 52,
          "draws": 3,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "o3",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-03T15:50:00Z",
          "losses": 65,
          "model": "o3",
          "point_rating_method": "sequential_elo",
          "public_id": "E-35751e26cd4e995d",
          "rated_matches": 151,
          "raw_elo_rating": 1506.9742217936025,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "first_pass",
          "score": 50.93146018801068,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 83
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 146,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 52,
          "draws": 6,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "o3",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 105,
          "model": "o3",
          "point_rating_method": "sequential_elo",
          "public_id": "E-432424671c9fea1c",
          "rated_matches": 146,
          "raw_elo_rating": 1217.3723017703346,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "first_pass",
          "score": 25.83877298968737,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 35
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 144,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 50,
          "draws": 4,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "o3",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-03T15:45:00Z",
          "losses": 52,
          "model": "o3",
          "point_rating_method": "sequential_elo",
          "public_id": "E-ead4229a85e5d554",
          "rated_matches": 144,
          "raw_elo_rating": 1661.179264242441,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "first_pass",
          "score": 64.20049924082426,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 88
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 88,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 42,
          "draws": 6,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "openai/gpt-oss-120b",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 32,
          "model": "openai/gpt-oss-120b",
          "point_rating_method": "sequential_elo",
          "public_id": "E-a97b527d9b41a80c",
          "rated_matches": 88,
          "raw_elo_rating": 1712.237284828002,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "repaired",
          "score": 67.82204727657161,
          "uncertainty": 9.249894000318006,
          "unilateral_faults": 0,
          "wins": 50
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 15,
          "capped_draws": 0,
          "coverage_status": "under_covered",
          "distinct_rated_opponents": 9,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "xhigh",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "qwen/qwen3.8-max",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-08-18T17:01:47Z",
          "losses": 7,
          "model": "qwen/qwen3.8-max",
          "point_rating_method": "sequential_elo",
          "public_id": "E-7a5171930c689e38",
          "rated_matches": 15,
          "raw_elo_rating": 1522.7378338885317,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "xhigh",
          "repair_status": "first_pass",
          "score": 46.45237289235433,
          "uncertainty": 81.25,
          "unilateral_faults": 0,
          "wins": 8
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 14,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 7,
          "draws": 1,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "max",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "stealth/ox-alpha",
            "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-08-22T00:27:26Z",
          "losses": 1,
          "model": "stealth/ox-alpha",
          "point_rating_method": "sequential_elo",
          "public_id": "E-2f1a60fc993600a0",
          "rated_matches": 14,
          "raw_elo_rating": 1635.0373727459369,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "max",
          "repair_status": "repaired",
          "score": 55.88064450050368,
          "uncertainty": 85.34944487358055,
          "unilateral_faults": 0,
          "wins": 12
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 14,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 7,
          "draws": 2,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "max",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "stealth/ox-alpha",
            "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-08-22T00:27:26Z",
          "losses": 0,
          "model": "stealth/ox-alpha",
          "point_rating_method": "sequential_elo",
          "public_id": "E-4d01a918377d78de",
          "rated_matches": 14,
          "raw_elo_rating": 1640.0055339758726,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "max",
          "repair_status": "first_pass",
          "score": 56.31030126798569,
          "uncertainty": 85.34944487358055,
          "unilateral_faults": 0,
          "wins": 12
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 14,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 7,
          "draws": 3,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "max",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "stealth/ox-alpha",
            "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-08-22T00:27:26Z",
          "losses": 7,
          "model": "stealth/ox-alpha",
          "point_rating_method": "sequential_elo",
          "public_id": "E-7c6550006514213b",
          "rated_matches": 14,
          "raw_elo_rating": 1455.9913598877981,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "max",
          "repair_status": "first_pass",
          "score": 40.396378279101896,
          "uncertainty": 85.34944487358055,
          "unilateral_faults": 0,
          "wins": 4
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 106,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 52,
          "draws": 2,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "stepfun/step-3.7-flash",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 64,
          "model": "stepfun/step-3.7-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-2d684425ca56be18",
          "rated_matches": 106,
          "raw_elo_rating": 1412.0094597124114,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "repaired",
          "score": 42.18034696924738,
          "uncertainty": 4.586824452283178,
          "unilateral_faults": 0,
          "wins": 40
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 90,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 43,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "tencent/hy3-preview",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 65,
          "model": "tencent/hy3-preview",
          "point_rating_method": "sequential_elo",
          "public_id": "E-3627e3dbf7a48738",
          "rated_matches": 90,
          "raw_elo_rating": 1236.8815002319625,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "first_pass",
          "score": 26.752823304656847,
          "uncertainty": 8.664241836095918,
          "unilateral_faults": 0,
          "wins": 25
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 156,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 54,
          "draws": 8,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "max",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "thinkingmachines/inkling",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 69,
          "model": "thinkingmachines/inkling",
          "point_rating_method": "sequential_elo",
          "public_id": "E-56e54327930d2f64",
          "rated_matches": 156,
          "raw_elo_rating": 1594.5323147640372,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "max",
          "repair_status": "repaired",
          "score": 58.54870417164183,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 79
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 16,
          "capped_draws": 0,
          "coverage_status": "under_covered",
          "distinct_rated_opponents": 9,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "max",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "thinkingmachines/inkling-small",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-08-18T19:25:55Z",
          "losses": 2,
          "model": "thinkingmachines/inkling-small",
          "point_rating_method": "sequential_elo",
          "public_id": "E-686068814c2242e8",
          "rated_matches": 16,
          "raw_elo_rating": 1608.3676756467582,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "max",
          "repair_status": "first_pass",
          "score": 54.116030920939295,
          "uncertainty": 77.5178125181665,
          "unilateral_faults": 0,
          "wins": 14
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 182,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 65,
          "draws": 13,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "x-ai/grok-4.5",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T14:00:00Z",
          "losses": 82,
          "model": "x-ai/grok-4.5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-5a1e23bce371a184",
          "rated_matches": 182,
          "raw_elo_rating": 1540.3129835742382,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "first_pass",
          "score": 54.06333802227879,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 87
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 72,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 36,
          "draws": 7,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "xiaomi/mimo-v2.5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T06:10:40Z",
          "losses": 30,
          "model": "xiaomi/mimo-v2.5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-51421c7ae2af8f7b",
          "rated_matches": 72,
          "raw_elo_rating": 1577.339884678403,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "repaired",
          "score": 55.77389183234963,
          "uncertainty": 14.770573598065289,
          "unilateral_faults": 0,
          "wins": 35
        }
      ],
      "GB2-07": [
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 94,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 44,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "xhigh",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-fable-5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 35,
          "model": "claude-fable-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-babd82321b910e7b",
          "rated_matches": 94,
          "raw_elo_rating": 1735.946996477361,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "xhigh",
          "repair_status": "first_pass",
          "score": 68.72658602086715,
          "uncertainty": 7.54891760425771,
          "unilateral_faults": 0,
          "wins": 59
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 170,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 61,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-opus-4-5",
            "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 77,
          "model": "claude-opus-4-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-e8719bed57f17312",
          "rated_matches": 170,
          "raw_elo_rating": 1502.1314410426282,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "first_pass",
          "score": 47.705624366124106,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 93
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 0,
          "capped_draws": 0,
          "coverage_status": "pending",
          "distinct_rated_opponents": 0,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "legacy_shared_thinking_budget",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-opus-4-5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "budget",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 0,
          "model": "claude-opus-4-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-f2d7a3f3bae22998",
          "rated_matches": 0,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "budget",
          "reasoning_setting": "legacy_shared_thinking_budget",
          "repair_status": "first_pass",
          "unilateral_faults": 0,
          "wins": 0
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 94,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 44,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "xhigh",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-opus-4-8",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-03T17:20:00Z",
          "losses": 21,
          "model": "claude-opus-4-8",
          "point_rating_method": "sequential_elo",
          "public_id": "E-5e09cecd1172d99b",
          "rated_matches": 94,
          "raw_elo_rating": 1824.9248359828734,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "xhigh",
          "repair_status": "first_pass",
          "score": 77.1003159963057,
          "uncertainty": 7.54891760425771,
          "unilateral_faults": 0,
          "wins": 73
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 82,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 37,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "xhigh",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-opus-5",
            "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-25T10:50:00Z",
          "losses": 1,
          "model": "claude-opus-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-1e882072d8d97548",
          "rated_matches": 82,
          "raw_elo_rating": 2071.119577926703,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "xhigh",
          "repair_status": "first_pass",
          "score": 100.0,
          "uncertainty": 11.132129994845172,
          "unilateral_faults": 0,
          "wins": 81
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 108,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 51,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "xhigh",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-sonnet-5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-03T16:50:00Z",
          "losses": 57,
          "model": "claude-sonnet-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-2146a36b46e938d6",
          "rated_matches": 108,
          "raw_elo_rating": 1474.8322523216139,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "xhigh",
          "repair_status": "first_pass",
          "score": 44.40955503896284,
          "uncertainty": 4.1413142610575715,
          "unilateral_faults": 0,
          "wins": 51
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 92,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 42,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "xhigh",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-sonnet-5",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 22,
          "model": "claude-sonnet-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-d751b3c423ad89f1",
          "rated_matches": 92,
          "raw_elo_rating": 1731.131155491913,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "xhigh",
          "repair_status": "first_pass",
          "score": 68.23205766874142,
          "uncertainty": 8.09758473652126,
          "unilateral_faults": 0,
          "wins": 70
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 96,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 45,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "xhigh",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "deepseek/deepseek-v4-flash",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 31,
          "model": "deepseek/deepseek-v4-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-ecf2a6ea6f9fe06c",
          "rated_matches": 96,
          "raw_elo_rating": 1770.709939839599,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "xhigh",
          "repair_status": "first_pass",
          "score": 72.03816050961174,
          "uncertainty": 7.017308256680951,
          "unilateral_faults": 0,
          "wins": 65
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 100,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 48,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "xhigh",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "deepseek/deepseek-v4-pro",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 56,
          "model": "deepseek/deepseek-v4-pro",
          "point_rating_method": "sequential_elo",
          "public_id": "E-f398fd6ac8c8bada",
          "rated_matches": 100,
          "raw_elo_rating": 1598.2368673537846,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "xhigh",
          "repair_status": "repaired",
          "score": 55.8831215680576,
          "uncertainty": 6.001859510499461,
          "unilateral_faults": 0,
          "wins": 44
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 106,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 51,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "google/gemini-3.1-flash-lite",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 70,
          "model": "google/gemini-3.1-flash-lite",
          "point_rating_method": "sequential_elo",
          "public_id": "E-0d43f308cfa4da52",
          "rated_matches": 106,
          "raw_elo_rating": 1479.7936186306395,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "repaired",
          "score": 44.84292897073299,
          "uncertainty": 4.586824452283178,
          "unilateral_faults": 0,
          "wins": 36
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 88,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 42,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "google/gemini-3.5-flash",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 42,
          "model": "google/gemini-3.5-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-f7f306cca2bb9532",
          "rated_matches": 88,
          "raw_elo_rating": 1663.7552103873281,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "repaired",
          "score": 61.804532842080334,
          "uncertainty": 9.249894000318006,
          "unilateral_faults": 0,
          "wins": 46
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 158,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 56,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "google/gemini-3.5-flash-lite",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 86,
          "model": "google/gemini-3.5-flash-lite",
          "point_rating_method": "sequential_elo",
          "public_id": "E-c4d27e5c752afb39",
          "rated_matches": 158,
          "raw_elo_rating": 1458.5252459156131,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "first_pass",
          "score": 43.49517776045333,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 72
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 157,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 60,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "google/gemini-3.5-flash-lite",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 76,
          "model": "google/gemini-3.5-flash-lite",
          "point_rating_method": "sequential_elo",
          "public_id": "E-f746ec3aee7874b2",
          "rated_matches": 157,
          "raw_elo_rating": 1486.0033232989615,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "first_pass",
          "score": 46.071715017764596,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 81
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 162,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 59,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "google/gemini-3.6-flash",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 74,
          "model": "google/gemini-3.6-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-f6ecc1626f38fa34",
          "rated_matches": 162,
          "raw_elo_rating": 1503.6788239490022,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "first_pass",
          "score": 47.781451793024814,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 88
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 96,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 47,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 43,
          "model": "gpt-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-15dad0db253c0497",
          "rated_matches": 96,
          "raw_elo_rating": 1613.540591357989,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "first_pass",
          "score": 57.24690808187588,
          "uncertainty": 7.017308256680951,
          "unilateral_faults": 0,
          "wins": 53
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 98,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 45,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "xhigh",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.4",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 11,
          "model": "gpt-5.4",
          "point_rating_method": "sequential_elo",
          "public_id": "E-80aa3ec3ac4ad97f",
          "rated_matches": 98,
          "raw_elo_rating": 1954.8997479714724,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "xhigh",
          "repair_status": "first_pass",
          "score": 89.41112100908529,
          "uncertainty": 6.501890762960602,
          "unilateral_faults": 0,
          "wins": 87
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 96,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 42,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "xhigh",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.4",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 7,
          "model": "gpt-5.4",
          "point_rating_method": "sequential_elo",
          "public_id": "E-9bc57dfe55b73887",
          "rated_matches": 96,
          "raw_elo_rating": 1906.2070120045769,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "xhigh",
          "repair_status": "first_pass",
          "score": 84.78982880227399,
          "uncertainty": 7.017308256680951,
          "unilateral_faults": 0,
          "wins": 89
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 98,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 46,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "xhigh",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 6,
          "model": "gpt-5.5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-6201278165db862a",
          "rated_matches": 98,
          "raw_elo_rating": 1985.8838134621776,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "xhigh",
          "repair_status": "first_pass",
          "score": 92.32704029193545,
          "uncertainty": 6.501890762960602,
          "unilateral_faults": 0,
          "wins": 92
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 96,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 44,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "xhigh",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.6-luna",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-10T05:30:29Z",
          "losses": 29,
          "model": "gpt-5.6-luna",
          "point_rating_method": "sequential_elo",
          "public_id": "E-73a7b73c1df452ad",
          "rated_matches": 96,
          "raw_elo_rating": 1821.0704465715448,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "xhigh",
          "repair_status": "first_pass",
          "score": 76.7776022306421,
          "uncertainty": 7.017308256680951,
          "unilateral_faults": 0,
          "wins": 67
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 90,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 43,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "xhigh",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.6-luna",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 20,
          "model": "gpt-5.6-luna",
          "point_rating_method": "sequential_elo",
          "public_id": "E-d86d2f05318f688d",
          "rated_matches": 90,
          "raw_elo_rating": 1757.382313941039,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "xhigh",
          "repair_status": "first_pass",
          "score": 70.65989910390739,
          "uncertainty": 8.664241836095918,
          "unilateral_faults": 0,
          "wins": 70
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 98,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 45,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "xhigh",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.6-sol",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-10T05:30:29Z",
          "losses": 30,
          "model": "gpt-5.6-sol",
          "point_rating_method": "sequential_elo",
          "public_id": "E-1b522c9c14f3860c",
          "rated_matches": 98,
          "raw_elo_rating": 1649.6684403120166,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "xhigh",
          "repair_status": "first_pass",
          "score": 60.68571517101774,
          "uncertainty": 6.501890762960602,
          "unilateral_faults": 0,
          "wins": 68
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 90,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 42,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "xhigh",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.6-sol",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 1,
          "model": "gpt-5.6-sol",
          "point_rating_method": "sequential_elo",
          "public_id": "E-475950cead6d8909",
          "rated_matches": 90,
          "raw_elo_rating": 1984.8748904849485,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "xhigh",
          "repair_status": "first_pass",
          "score": 92.06929067805841,
          "uncertainty": 8.664241836095918,
          "unilateral_faults": 0,
          "wins": 89
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 94,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 46,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "xhigh",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.6-terra",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-10T05:30:29Z",
          "losses": 29,
          "model": "gpt-5.6-terra",
          "point_rating_method": "sequential_elo",
          "public_id": "E-65bf9818e3e1b632",
          "rated_matches": 94,
          "raw_elo_rating": 1780.4659593446845,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "xhigh",
          "repair_status": "first_pass",
          "score": 72.91627837470821,
          "uncertainty": 7.54891760425771,
          "unilateral_faults": 0,
          "wins": 65
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 96,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 47,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "mistralai/mistral-medium-3-5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 75,
          "model": "mistralai/mistral-medium-3-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-d0d0df9d83b6e37e",
          "rated_matches": 96,
          "raw_elo_rating": 1213.7066599409454,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "first_pass",
          "score": 19.618422210437004,
          "uncertainty": 7.017308256680951,
          "unilateral_faults": 0,
          "wins": 21
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 180,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 65,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "max",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "moonshotai/kimi-k3",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T14:00:00Z",
          "losses": 68,
          "model": "moonshotai/kimi-k3",
          "point_rating_method": "sequential_elo",
          "public_id": "E-1d1372c78963efdf",
          "rated_matches": 180,
          "raw_elo_rating": 1612.648077127973,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "max",
          "repair_status": "repaired",
          "score": 58.18702905042954,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 112
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 161,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 59,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "o3",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-03T15:50:00Z",
          "losses": 87,
          "model": "o3",
          "point_rating_method": "sequential_elo",
          "public_id": "E-43c337fb7f5e535e",
          "rated_matches": 161,
          "raw_elo_rating": 1439.950195908931,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "first_pass",
          "score": 41.77484599142675,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 74
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 155,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 59,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "o3",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-03T15:45:00Z",
          "losses": 84,
          "model": "o3",
          "point_rating_method": "sequential_elo",
          "public_id": "E-541cee4461c65fcb",
          "rated_matches": 155,
          "raw_elo_rating": 1498.0682698361927,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "first_pass",
          "score": 47.18801426535529,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 71
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 162,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 58,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "o3",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 74,
          "model": "o3",
          "point_rating_method": "sequential_elo",
          "public_id": "E-bc20ac8102f6a0ac",
          "rated_matches": 162,
          "raw_elo_rating": 1648.1552922799856,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "first_pass",
          "score": 61.378173632216026,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 88
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 158,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 59,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "o3",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-03T16:00:00Z",
          "losses": 105,
          "model": "o3",
          "point_rating_method": "sequential_elo",
          "public_id": "E-ee95d01578313864",
          "rated_matches": 158,
          "raw_elo_rating": 1318.4051069389095,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "first_pass",
          "score": 30.308431325245213,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 53
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 96,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 47,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "openai/gpt-oss-120b",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 65,
          "model": "openai/gpt-oss-120b",
          "point_rating_method": "sequential_elo",
          "public_id": "E-29bc7f4fdf0f7b14",
          "rated_matches": 96,
          "raw_elo_rating": 1426.4652985743849,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "repaired",
          "score": 39.64119866533117,
          "uncertainty": 7.017308256680951,
          "unilateral_faults": 0,
          "wins": 31
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 20,
          "capped_draws": 0,
          "coverage_status": "under_covered",
          "distinct_rated_opponents": 8,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "xhigh",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "qwen/qwen3.8-max",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 0,
          "model": "qwen/qwen3.8-max",
          "point_rating_method": "sequential_elo",
          "public_id": "E-1c3cd7cd7b39b7ff",
          "rated_matches": 20,
          "raw_elo_rating": 1746.3008626110957,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "xhigh",
          "repair_status": "first_pass",
          "score": 65.34857672458816,
          "uncertainty": 65.3589451179962,
          "unilateral_faults": 0,
          "wins": 20
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 16,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 8,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "max",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "stealth/ox-alpha",
            "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-08-22T00:27:26Z",
          "losses": 4,
          "model": "stealth/ox-alpha",
          "point_rating_method": "sequential_elo",
          "public_id": "E-27243ca72bb71e47",
          "rated_matches": 16,
          "raw_elo_rating": 1601.6512786766596,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "max",
          "repair_status": "first_pass",
          "score": 50.82014332989595,
          "uncertainty": 77.5178125181665,
          "unilateral_faults": 0,
          "wins": 12
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 16,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 8,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "max",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "stealth/ox-alpha",
            "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-08-22T00:27:26Z",
          "losses": 5,
          "model": "stealth/ox-alpha",
          "point_rating_method": "sequential_elo",
          "public_id": "E-6160aff1d9ab7bd7",
          "rated_matches": 16,
          "raw_elo_rating": 1559.7727172879754,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "max",
          "repair_status": "first_pass",
          "score": 46.878939915904965,
          "uncertainty": 77.5178125181665,
          "unilateral_faults": 0,
          "wins": 11
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 16,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 8,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "max",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "stealth/ox-alpha",
            "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-08-22T00:27:26Z",
          "losses": 8,
          "model": "stealth/ox-alpha",
          "point_rating_method": "sequential_elo",
          "public_id": "E-9f68949b5725fa77",
          "rated_matches": 16,
          "raw_elo_rating": 1512.3951665763,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "max",
          "repair_status": "first_pass",
          "score": 42.420225040808035,
          "uncertainty": 77.5178125181665,
          "unilateral_faults": 0,
          "wins": 8
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 101,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 50,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "stepfun/step-3.7-flash",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 66,
          "model": "stepfun/step-3.7-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-6a5e44fe2dde4257",
          "rated_matches": 101,
          "raw_elo_rating": 1349.1712838775788,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "repaired",
          "score": 32.46189477313855,
          "uncertainty": 5.757377148833722,
          "unilateral_faults": 0,
          "wins": 35
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 104,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 50,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "tencent/hy3-preview",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 67,
          "model": "tencent/hy3-preview",
          "point_rating_method": "sequential_elo",
          "public_id": "E-dfed1e345a939bcd",
          "rated_matches": 104,
          "raw_elo_rating": 1276.1948853703204,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "first_pass",
          "score": 25.647698335291103,
          "uncertainty": 5.045003647426665,
          "unilateral_faults": 0,
          "wins": 37
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 174,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 66,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "max",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "thinkingmachines/inkling",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 129,
          "model": "thinkingmachines/inkling",
          "point_rating_method": "sequential_elo",
          "public_id": "E-38e756fc6f3a2db6",
          "rated_matches": 174,
          "raw_elo_rating": 1268.3605173911951,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "max",
          "repair_status": "repaired",
          "score": 25.73846555139435,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 45
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 16,
          "capped_draws": 0,
          "coverage_status": "under_covered",
          "distinct_rated_opponents": 9,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "max",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "thinkingmachines/inkling-small",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 15,
          "model": "thinkingmachines/inkling-small",
          "point_rating_method": "sequential_elo",
          "public_id": "E-516d381904063142",
          "rated_matches": 16,
          "raw_elo_rating": 1304.7852176135736,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "max",
          "repair_status": "first_pass",
          "score": 22.881993246353847,
          "uncertainty": 77.5178125181665,
          "unilateral_faults": 0,
          "wins": 1
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 166,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 66,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "x-ai/grok-4.5",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T14:00:00Z",
          "losses": 62,
          "model": "x-ai/grok-4.5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-436a3933a93e10cd",
          "rated_matches": 166,
          "raw_elo_rating": 1657.3711692973993,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "first_pass",
          "score": 62.28100802900767,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 104
        }
      ],
      "GB2-08": [
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 102,
          "capped_draws": 1,
          "coverage_status": "rated",
          "distinct_rated_opponents": 48,
          "draws": 1,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "xhigh",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-fable-5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 4,
          "model": "claude-fable-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-12891afa894223fd",
          "rated_matches": 102,
          "raw_elo_rating": 2070.226734381098,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "xhigh",
          "repair_status": "repaired",
          "score": 100.0,
          "uncertainty": 5.516463908214657,
          "unilateral_faults": 0,
          "wins": 97
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 0,
          "capped_draws": 0,
          "coverage_status": "pending",
          "distinct_rated_opponents": 0,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "legacy_shared_thinking_budget",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-opus-4-5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "budget",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 0,
          "model": "claude-opus-4-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-6a0c04b4335bfea0",
          "rated_matches": 0,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "budget",
          "reasoning_setting": "legacy_shared_thinking_budget",
          "repair_status": "first_pass",
          "unilateral_faults": 0,
          "wins": 0
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 186,
          "capped_draws": 99,
          "coverage_status": "rated",
          "distinct_rated_opponents": 65,
          "draws": 99,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-opus-4-5",
            "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 70,
          "model": "claude-opus-4-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-877eec51affacb3a",
          "rated_matches": 186,
          "raw_elo_rating": 1346.2739670506865,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "first_pass",
          "score": 27.83360360167963,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 17
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 100,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 47,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "xhigh",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-opus-4-8",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-03T17:20:00Z",
          "losses": 23,
          "model": "claude-opus-4-8",
          "point_rating_method": "sequential_elo",
          "public_id": "E-22dc6fe5ae5fb8b1",
          "rated_matches": 100,
          "raw_elo_rating": 1792.3813910887834,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "xhigh",
          "repair_status": "first_pass",
          "score": 71.86972819787296,
          "uncertainty": 6.001859510499461,
          "unilateral_faults": 0,
          "wins": 77
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 86,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 37,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "xhigh",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-opus-5",
            "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-25T15:48:01Z",
          "losses": 13,
          "model": "claude-opus-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-a40851c4f03704e5",
          "rated_matches": 86,
          "raw_elo_rating": 1903.459258801908,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "xhigh",
          "repair_status": "first_pass",
          "score": 82.78833738661038,
          "uncertainty": 9.855626741889738,
          "unilateral_faults": 0,
          "wins": 73
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 88,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 40,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "xhigh",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-opus-5",
            "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-25T15:48:01Z",
          "losses": 26,
          "model": "claude-opus-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-f5914ca845403384",
          "rated_matches": 88,
          "raw_elo_rating": 1692.3978760053656,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "xhigh",
          "repair_status": "first_pass",
          "score": 61.498380849791204,
          "uncertainty": 9.249894000318006,
          "unilateral_faults": 0,
          "wins": 62
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 102,
          "capped_draws": 55,
          "coverage_status": "rated",
          "distinct_rated_opponents": 49,
          "draws": 55,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "xhigh",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-sonnet-5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-03T16:50:00Z",
          "losses": 38,
          "model": "claude-sonnet-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-b5805acb90227d50",
          "rated_matches": 102,
          "raw_elo_rating": 1427.5092315776758,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "xhigh",
          "repair_status": "first_pass",
          "score": 35.019299747841444,
          "uncertainty": 5.516463908214657,
          "unilateral_faults": 0,
          "wins": 9
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 90,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 42,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "xhigh",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-sonnet-5",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 13,
          "model": "claude-sonnet-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-df0550ce48a0b895",
          "rated_matches": 90,
          "raw_elo_rating": 1884.7508193563601,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "xhigh",
          "repair_status": "first_pass",
          "score": 80.99321920419641,
          "uncertainty": 8.664241836095918,
          "unilateral_faults": 0,
          "wins": 77
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 108,
          "capped_draws": 77,
          "coverage_status": "rated",
          "distinct_rated_opponents": 54,
          "draws": 77,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "xhigh",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "deepseek/deepseek-v4-flash",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 29,
          "model": "deepseek/deepseek-v4-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-a7310645c3b96434",
          "rated_matches": 108,
          "raw_elo_rating": 1398.1860928220167,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "xhigh",
          "repair_status": "repaired",
          "score": 32.16586642400081,
          "uncertainty": 4.1413142610575715,
          "unilateral_faults": 0,
          "wins": 2
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 94,
          "capped_draws": 65,
          "coverage_status": "rated",
          "distinct_rated_opponents": 44,
          "draws": 65,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "xhigh",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "deepseek/deepseek-v4-pro",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 25,
          "model": "deepseek/deepseek-v4-pro",
          "point_rating_method": "sequential_elo",
          "public_id": "E-3a5b5c4507a989d3",
          "rated_matches": 94,
          "raw_elo_rating": 1387.905101445435,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "xhigh",
          "repair_status": "repaired",
          "score": 30.850811557145292,
          "uncertainty": 7.54891760425771,
          "unilateral_faults": 0,
          "wins": 4
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 106,
          "capped_draws": 72,
          "coverage_status": "rated",
          "distinct_rated_opponents": 51,
          "draws": 72,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "google/gemini-3.1-flash-lite",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 28,
          "model": "google/gemini-3.1-flash-lite",
          "point_rating_method": "sequential_elo",
          "public_id": "E-b335c9f92035f80b",
          "rated_matches": 106,
          "raw_elo_rating": 1381.0312376325182,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "repaired",
          "score": 30.395424278997872,
          "uncertainty": 4.586824452283178,
          "unilateral_faults": 0,
          "wins": 6
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 96,
          "capped_draws": 62,
          "coverage_status": "rated",
          "distinct_rated_opponents": 48,
          "draws": 62,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "google/gemini-3.5-flash",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 34,
          "model": "google/gemini-3.5-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-fa332e578ae97122",
          "rated_matches": 96,
          "raw_elo_rating": 1296.1001435676862,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "repaired",
          "score": 21.612048110556422,
          "uncertainty": 7.017308256680951,
          "unilateral_faults": 0,
          "wins": 0
        },
        {
          "admitted_plugin_count": 2,
          "attempted_matches": 170,
          "capped_draws": 102,
          "coverage_status": "rated",
          "distinct_rated_opponents": 62,
          "draws": 102,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "google/gemini-3.5-flash-lite",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 61,
          "model": "google/gemini-3.5-flash-lite",
          "point_rating_method": "sequential_elo",
          "public_id": "E-2a14d2f80ade1bda",
          "rated_matches": 170,
          "raw_elo_rating": 1329.5503292837363,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "first_pass",
          "score": 26.007530314351136,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 7
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 158,
          "capped_draws": 24,
          "coverage_status": "rated",
          "distinct_rated_opponents": 62,
          "draws": 24,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "google/gemini-3.6-flash",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 26,
          "model": "google/gemini-3.6-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-620b5ca2bcd82419",
          "rated_matches": 158,
          "raw_elo_rating": 1771.3527786328943,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "first_pass",
          "score": 70.56052575945287,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 108
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 156,
          "capped_draws": 83,
          "coverage_status": "rated",
          "distinct_rated_opponents": 62,
          "draws": 83,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "google/gemini-3.6-flash",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 64,
          "model": "google/gemini-3.6-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-efad9f3f4e9183a0",
          "rated_matches": 156,
          "raw_elo_rating": 1352.379641990491,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "first_pass",
          "score": 28.18070013372008,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 9
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 114,
          "capped_draws": 66,
          "coverage_status": "rated",
          "distinct_rated_opponents": 57,
          "draws": 66,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 32,
          "model": "gpt-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-ebca8ea756b4a4ad",
          "rated_matches": 114,
          "raw_elo_rating": 1417.3165817886681,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "first_pass",
          "score": 34.20242036213885,
          "uncertainty": 2.875240412015687,
          "unilateral_faults": 0,
          "wins": 16
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 86,
          "capped_draws": 11,
          "coverage_status": "rated",
          "distinct_rated_opponents": 42,
          "draws": 11,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "xhigh",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.4",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 23,
          "model": "gpt-5.4",
          "point_rating_method": "sequential_elo",
          "public_id": "E-431ff31b9cd599e1",
          "rated_matches": 86,
          "raw_elo_rating": 1650.2502481709378,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "xhigh",
          "repair_status": "first_pass",
          "score": 57.188133954793884,
          "uncertainty": 9.855626741889738,
          "unilateral_faults": 0,
          "wins": 52
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 102,
          "capped_draws": 26,
          "coverage_status": "rated",
          "distinct_rated_opponents": 48,
          "draws": 26,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "xhigh",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.4",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 31,
          "model": "gpt-5.4",
          "point_rating_method": "sequential_elo",
          "public_id": "E-ddc1f3e68bf1e74a",
          "rated_matches": 102,
          "raw_elo_rating": 1614.3353490460158,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "xhigh",
          "repair_status": "first_pass",
          "score": 53.907990168643416,
          "uncertainty": 5.516463908214657,
          "unilateral_faults": 0,
          "wins": 45
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 104,
          "capped_draws": 16,
          "coverage_status": "rated",
          "distinct_rated_opponents": 47,
          "draws": 16,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "xhigh",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 24,
          "model": "gpt-5.5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-3e859a6b27767128",
          "rated_matches": 104,
          "raw_elo_rating": 1793.2236111969223,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "xhigh",
          "repair_status": "first_pass",
          "score": 72.03227205758726,
          "uncertainty": 5.045003647426665,
          "unilateral_faults": 0,
          "wins": 64
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 94,
          "capped_draws": 7,
          "coverage_status": "rated",
          "distinct_rated_opponents": 46,
          "draws": 7,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "xhigh",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.6-luna",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-10T05:30:29Z",
          "losses": 31,
          "model": "gpt-5.6-luna",
          "point_rating_method": "sequential_elo",
          "public_id": "E-0fb7de4e8156a229",
          "rated_matches": 94,
          "raw_elo_rating": 1659.815042678165,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "xhigh",
          "repair_status": "first_pass",
          "score": 58.34173612315974,
          "uncertainty": 7.54891760425771,
          "unilateral_faults": 0,
          "wins": 56
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 88,
          "capped_draws": 51,
          "coverage_status": "rated",
          "distinct_rated_opponents": 42,
          "draws": 51,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "xhigh",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.6-luna",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 35,
          "model": "gpt-5.6-luna",
          "point_rating_method": "sequential_elo",
          "public_id": "E-ca2978e1aca13fec",
          "rated_matches": 88,
          "raw_elo_rating": 1316.0178733440812,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "xhigh",
          "repair_status": "first_pass",
          "score": 23.445214369711753,
          "uncertainty": 9.249894000318006,
          "unilateral_faults": 0,
          "wins": 2
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 88,
          "capped_draws": 13,
          "coverage_status": "rated",
          "distinct_rated_opponents": 43,
          "draws": 13,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "xhigh",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.6-sol",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-10T05:30:29Z",
          "losses": 52,
          "model": "gpt-5.6-sol",
          "point_rating_method": "sequential_elo",
          "public_id": "E-3ae62f195160add3",
          "rated_matches": 88,
          "raw_elo_rating": 1356.219884706978,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "xhigh",
          "repair_status": "first_pass",
          "score": 27.509760361553635,
          "uncertainty": 9.249894000318006,
          "unilateral_faults": 0,
          "wins": 23
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 92,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 42,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "xhigh",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.6-sol",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 17,
          "model": "gpt-5.6-sol",
          "point_rating_method": "sequential_elo",
          "public_id": "E-58adff67f80afed1",
          "rated_matches": 92,
          "raw_elo_rating": 1859.6856893973443,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "xhigh",
          "repair_status": "first_pass",
          "score": 78.50489070907093,
          "uncertainty": 8.09758473652126,
          "unilateral_faults": 0,
          "wins": 75
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 100,
          "capped_draws": 15,
          "coverage_status": "rated",
          "distinct_rated_opponents": 47,
          "draws": 15,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "xhigh",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.6-terra",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-10T05:30:29Z",
          "losses": 33,
          "model": "gpt-5.6-terra",
          "point_rating_method": "sequential_elo",
          "public_id": "E-b061663dc342c859",
          "rated_matches": 100,
          "raw_elo_rating": 1623.2810218217542,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "xhigh",
          "repair_status": "repaired",
          "score": 54.77316499562428,
          "uncertainty": 6.001859510499461,
          "unilateral_faults": 0,
          "wins": 52
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 104,
          "capped_draws": 68,
          "coverage_status": "rated",
          "distinct_rated_opponents": 51,
          "draws": 68,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "nvidia/nemotron-3-ultra-550b-a55b",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-11T17:22:09Z",
          "losses": 26,
          "model": "nvidia/nemotron-3-ultra-550b-a55b",
          "point_rating_method": "sequential_elo",
          "public_id": "E-2e3c01d0103fc439",
          "rated_matches": 104,
          "raw_elo_rating": 1398.2805327368721,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "repaired",
          "score": 32.102321984441986,
          "uncertainty": 5.045003647426665,
          "unilateral_faults": 0,
          "wins": 10
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 92,
          "capped_draws": 64,
          "coverage_status": "rated",
          "distinct_rated_opponents": 44,
          "draws": 64,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "nvidia/nemotron-3-ultra-550b-a55b",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 23,
          "model": "nvidia/nemotron-3-ultra-550b-a55b",
          "point_rating_method": "sequential_elo",
          "public_id": "E-8c24e8bcbe9b1228",
          "rated_matches": 92,
          "raw_elo_rating": 1397.4647466210838,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "first_pass",
          "score": 31.77294331102291,
          "uncertainty": 8.09758473652126,
          "unilateral_faults": 0,
          "wins": 5
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 158,
          "capped_draws": 1,
          "coverage_status": "rated",
          "distinct_rated_opponents": 62,
          "draws": 1,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "o3",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-03T16:00:00Z",
          "losses": 35,
          "model": "o3",
          "point_rating_method": "sequential_elo",
          "public_id": "E-2270b9df7d2b32cc",
          "rated_matches": 158,
          "raw_elo_rating": 1799.6635648752338,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "first_pass",
          "score": 73.42283261540769,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 122
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 152,
          "capped_draws": 84,
          "coverage_status": "rated",
          "distinct_rated_opponents": 62,
          "draws": 84,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "o3",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-03T15:45:00Z",
          "losses": 60,
          "model": "o3",
          "point_rating_method": "sequential_elo",
          "public_id": "E-9fbb8e6c69f575f4",
          "rated_matches": 152,
          "raw_elo_rating": 1318.8921498651468,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "first_pass",
          "score": 24.753094391039728,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 8
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 168,
          "capped_draws": 106,
          "coverage_status": "rated",
          "distinct_rated_opponents": 64,
          "draws": 106,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "o3",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 50,
          "model": "o3",
          "point_rating_method": "sequential_elo",
          "public_id": "E-afa6c09eebc859c4",
          "rated_matches": 168,
          "raw_elo_rating": 1410.309112947049,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "first_pass",
          "score": 34.154244022339505,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 12
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 94,
          "capped_draws": 67,
          "coverage_status": "rated",
          "distinct_rated_opponents": 45,
          "draws": 67,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "openai/gpt-oss-120b",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 22,
          "model": "openai/gpt-oss-120b",
          "point_rating_method": "sequential_elo",
          "public_id": "E-24a75273941e6ea3",
          "rated_matches": 94,
          "raw_elo_rating": 1400.2862698488254,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "repaired",
          "score": 32.10258545358184,
          "uncertainty": 7.54891760425771,
          "unilateral_faults": 0,
          "wins": 5
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 18,
          "capped_draws": 12,
          "coverage_status": "under_covered",
          "distinct_rated_opponents": 8,
          "draws": 12,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "xhigh",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "qwen/qwen3.8-max",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-08-18T17:01:47Z",
          "losses": 4,
          "model": "qwen/qwen3.8-max",
          "point_rating_method": "sequential_elo",
          "public_id": "E-eef649e110a96b98",
          "rated_matches": 18,
          "raw_elo_rating": 1453.2655519062441,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "xhigh",
          "repair_status": "first_pass",
          "score": 32.3302819181756,
          "uncertainty": 70.95786693528086,
          "unilateral_faults": 0,
          "wins": 2
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 14,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 7,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "max",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "stealth/ox-alpha",
            "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-08-22T00:27:26Z",
          "losses": 0,
          "model": "stealth/ox-alpha",
          "point_rating_method": "sequential_elo",
          "public_id": "E-27b1ec2d9d5762a4",
          "rated_matches": 14,
          "raw_elo_rating": 1670.7371927792685,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "max",
          "repair_status": "first_pass",
          "score": 53.153302297748226,
          "uncertainty": 85.34944487358055,
          "unilateral_faults": 0,
          "wins": 14
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 14,
          "capped_draws": 7,
          "coverage_status": "rated",
          "distinct_rated_opponents": 7,
          "draws": 7,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "max",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "stealth/ox-alpha",
            "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-08-22T00:27:26Z",
          "losses": 4,
          "model": "stealth/ox-alpha",
          "point_rating_method": "sequential_elo",
          "public_id": "E-ec8f506d56ff547e",
          "rated_matches": 14,
          "raw_elo_rating": 1481.0792078166126,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "max",
          "repair_status": "first_pass",
          "score": 33.9783014341789,
          "uncertainty": 85.34944487358055,
          "unilateral_faults": 0,
          "wins": 3
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 14,
          "capped_draws": 3,
          "coverage_status": "rated",
          "distinct_rated_opponents": 7,
          "draws": 3,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "max",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "stealth/ox-alpha",
            "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-08-22T00:27:26Z",
          "losses": 3,
          "model": "stealth/ox-alpha",
          "point_rating_method": "sequential_elo",
          "public_id": "E-f84aa60bad19339a",
          "rated_matches": 14,
          "raw_elo_rating": 1559.7380795164838,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "max",
          "repair_status": "first_pass",
          "score": 41.93095332526276,
          "uncertainty": 85.34944487358055,
          "unilateral_faults": 0,
          "wins": 8
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 92,
          "capped_draws": 70,
          "coverage_status": "rated",
          "distinct_rated_opponents": 44,
          "draws": 70,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "stepfun/step-3.7-flash",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 21,
          "model": "stepfun/step-3.7-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-8b265019ada47f24",
          "rated_matches": 92,
          "raw_elo_rating": 1385.5425180436987,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "repaired",
          "score": 30.56756963106926,
          "uncertainty": 8.09758473652126,
          "unilateral_faults": 0,
          "wins": 1
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 104,
          "capped_draws": 26,
          "coverage_status": "rated",
          "distinct_rated_opponents": 51,
          "draws": 26,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "tencent/hy3-preview",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 45,
          "model": "tencent/hy3-preview",
          "point_rating_method": "sequential_elo",
          "public_id": "E-81a5e5ef15f371dc",
          "rated_matches": 104,
          "raw_elo_rating": 1457.8491002180717,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "first_pass",
          "score": 38.12488588080784,
          "uncertainty": 5.045003647426665,
          "unilateral_faults": 0,
          "wins": 33
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 178,
          "capped_draws": 103,
          "coverage_status": "rated",
          "distinct_rated_opponents": 67,
          "draws": 103,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "max",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "thinkingmachines/inkling",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 71,
          "model": "thinkingmachines/inkling",
          "point_rating_method": "sequential_elo",
          "public_id": "E-d21921560d198b28",
          "rated_matches": 178,
          "raw_elo_rating": 1337.923250186877,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "max",
          "repair_status": "repaired",
          "score": 26.923956847273455,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 4
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 17,
          "capped_draws": 16,
          "coverage_status": "under_covered",
          "distinct_rated_opponents": 8,
          "draws": 16,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "max",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "thinkingmachines/inkling-small",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 1,
          "model": "thinkingmachines/inkling-small",
          "point_rating_method": "sequential_elo",
          "public_id": "E-888363fef76ee16a",
          "rated_matches": 17,
          "raw_elo_rating": 1468.4221652498795,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "max",
          "repair_status": "repaired",
          "score": 33.608426961121125,
          "uncertainty": 74.10113019775793,
          "unilateral_faults": 0,
          "wins": 0
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 178,
          "capped_draws": 2,
          "coverage_status": "rated",
          "distinct_rated_opponents": 68,
          "draws": 2,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "x-ai/grok-4.5",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T14:00:00Z",
          "losses": 20,
          "model": "x-ai/grok-4.5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-707dd709e358a173",
          "rated_matches": 178,
          "raw_elo_rating": 1958.1843507591848,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "first_pass",
          "score": 89.63424632680322,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 156
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 78,
          "capped_draws": 71,
          "coverage_status": "rated",
          "distinct_rated_opponents": 39,
          "draws": 71,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "xiaomi/mimo-v2.5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T06:10:40Z",
          "losses": 5,
          "model": "xiaomi/mimo-v2.5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-5f664f9580459829",
          "rated_matches": 78,
          "raw_elo_rating": 1390.6857995210323,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "repaired",
          "score": 30.7311375060473,
          "uncertainty": 12.5043950463012,
          "unilateral_faults": 0,
          "wins": 2
        }
      ]
    },
    "full_freedom/mixed": {
      "GB2-01": [
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 88,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 43,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-fable-5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 26,
          "model": "claude-fable-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-2dbc6efbd7db03b5",
          "rated_matches": 86,
          "raw_elo_rating": 1746.9451046530367,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 71.4108605082153,
          "uncertainty": 9.855626741889738,
          "unilateral_faults": 2,
          "wins": 60
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 102,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 47,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "xhigh",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-fable-5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-03T17:50:00Z",
          "losses": 35,
          "model": "claude-fable-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-8000131e469a8bb6",
          "rated_matches": 102,
          "raw_elo_rating": 1824.3873130220802,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "xhigh",
          "repair_status": "first_pass",
          "score": 79.58869492247467,
          "uncertainty": 5.516463908214657,
          "unilateral_faults": 0,
          "wins": 67
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 118,
          "capped_draws": 77,
          "coverage_status": "rated",
          "distinct_rated_opponents": 58,
          "draws": 77,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-opus-4-5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "omitted",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 26,
          "model": "claude-opus-4-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-2e3eca63f7980fac",
          "rated_matches": 118,
          "raw_elo_rating": 1426.0475483689286,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "omitted",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 39.60642935936982,
          "uncertainty": 2.084924851410568,
          "unilateral_faults": 0,
          "wins": 15
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 0,
          "capped_draws": 0,
          "coverage_status": "pending",
          "distinct_rated_opponents": 0,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "legacy_shared_thinking_budget",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-opus-4-5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "budget",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 0,
          "model": "claude-opus-4-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-53c8add70ed7d2e7",
          "rated_matches": 0,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "budget",
          "reasoning_setting": "legacy_shared_thinking_budget",
          "repair_status": "first_pass",
          "unilateral_faults": 0,
          "wins": 0
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 153,
          "capped_draws": 26,
          "coverage_status": "rated",
          "distinct_rated_opponents": 60,
          "draws": 26,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-opus-4-5",
            "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 36,
          "model": "claude-opus-4-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-5b675f86b98132f4",
          "rated_matches": 153,
          "raw_elo_rating": 1662.883091394821,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "first_pass",
          "score": 63.991356251926845,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 91
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 0,
          "capped_draws": 0,
          "coverage_status": "pending",
          "distinct_rated_opponents": 0,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "legacy_shared_thinking_budget",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-opus-4-5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "budget",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 0,
          "model": "claude-opus-4-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-7631f602d0516364",
          "rated_matches": 0,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "budget",
          "reasoning_setting": "legacy_shared_thinking_budget",
          "repair_status": "first_pass",
          "unilateral_faults": 0,
          "wins": 0
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 178,
          "capped_draws": 51,
          "coverage_status": "rated",
          "distinct_rated_opponents": 72,
          "draws": 51,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-opus-4-5",
            "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 43,
          "model": "claude-opus-4-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-829b603611fbdcef",
          "rated_matches": 178,
          "raw_elo_rating": 1593.5115898273448,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 57.216109384642444,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 84
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 94,
          "capped_draws": 17,
          "coverage_status": "rated",
          "distinct_rated_opponents": 46,
          "draws": 17,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-opus-4-8",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 39,
          "model": "claude-opus-4-8",
          "point_rating_method": "sequential_elo",
          "public_id": "E-13ec9509bc80f2bf",
          "rated_matches": 94,
          "raw_elo_rating": 1470.264528764638,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 43.63359523406752,
          "uncertainty": 7.54891760425771,
          "unilateral_faults": 0,
          "wins": 38
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 108,
          "capped_draws": 18,
          "coverage_status": "rated",
          "distinct_rated_opponents": 49,
          "draws": 18,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "xhigh",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-opus-4-8",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-03T17:20:00Z",
          "losses": 36,
          "model": "claude-opus-4-8",
          "point_rating_method": "sequential_elo",
          "public_id": "E-3308d2952452916e",
          "rated_matches": 108,
          "raw_elo_rating": 1609.684924746103,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "xhigh",
          "repair_status": "first_pass",
          "score": 58.000169538136674,
          "uncertainty": 4.1413142610575715,
          "unilateral_faults": 0,
          "wins": 54
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 88,
          "capped_draws": 23,
          "coverage_status": "rated",
          "distinct_rated_opponents": 44,
          "draws": 23,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-opus-4-8",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "omitted",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 24,
          "model": "claude-opus-4-8",
          "point_rating_method": "sequential_elo",
          "public_id": "E-757a6149e87d8b53",
          "rated_matches": 88,
          "raw_elo_rating": 1564.0122470382578,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "omitted",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 52.971032291512834,
          "uncertainty": 9.249894000318006,
          "unilateral_faults": 0,
          "wins": 41
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 116,
          "capped_draws": 14,
          "coverage_status": "rated",
          "distinct_rated_opponents": 58,
          "draws": 14,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-opus-5",
            "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-25T15:48:00Z",
          "losses": 41,
          "model": "claude-opus-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-0437af9582860271",
          "rated_matches": 116,
          "raw_elo_rating": 1600.2178597089212,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 57.178073203245866,
          "uncertainty": 2.4750163521024238,
          "unilateral_faults": 0,
          "wins": 61
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 122,
          "capped_draws": 89,
          "coverage_status": "rated",
          "distinct_rated_opponents": 59,
          "draws": 89,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-opus-5",
            "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-25T15:48:00Z",
          "losses": 14,
          "model": "claude-opus-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-6c30dc38efb07e9e",
          "rated_matches": 121,
          "raw_elo_rating": 1541.7900362821504,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 51.350232950765154,
          "uncertainty": 1.5178730212592662,
          "unilateral_faults": 0,
          "wins": 18
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 70,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 29,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "xhigh",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-opus-5",
            "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-25T15:48:00Z",
          "losses": 18,
          "model": "claude-opus-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-700f3dddd611df07",
          "rated_matches": 70,
          "raw_elo_rating": 1853.021779157713,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "xhigh",
          "repair_status": "first_pass",
          "score": 81.66832408200672,
          "uncertainty": 15.58908290969266,
          "unilateral_faults": 0,
          "wins": 52
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 120,
          "capped_draws": 16,
          "coverage_status": "rated",
          "distinct_rated_opponents": 58,
          "draws": 16,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-opus-5",
            "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-25T15:48:00Z",
          "losses": 9,
          "model": "claude-opus-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-865d68ab219fd7ee",
          "rated_matches": 120,
          "raw_elo_rating": 1893.5408887472404,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 86.8861767990556,
          "uncertainty": 1.7045454545454586,
          "unilateral_faults": 0,
          "wins": 95
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 94,
          "capped_draws": 5,
          "coverage_status": "rated",
          "distinct_rated_opponents": 47,
          "draws": 5,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-opus-5",
            "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-25T15:48:00Z",
          "losses": 23,
          "model": "claude-opus-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-93a6875407c22137",
          "rated_matches": 94,
          "raw_elo_rating": 1810.8029618970652,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 78.05140670041531,
          "uncertainty": 7.54891760425771,
          "unilateral_faults": 0,
          "wins": 66
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 58,
          "capped_draws": 2,
          "coverage_status": "rated",
          "distinct_rated_opponents": 28,
          "draws": 2,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "xhigh",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-opus-5",
            "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-25T15:48:00Z",
          "losses": 29,
          "model": "claude-opus-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-bf06fe9df8858291",
          "rated_matches": 58,
          "raw_elo_rating": 1467.974430458784,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "xhigh",
          "repair_status": "first_pass",
          "score": 42.28669895236079,
          "uncertainty": 21.344455490411935,
          "unilateral_faults": 0,
          "wins": 27
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 178,
          "capped_draws": 128,
          "coverage_status": "rated",
          "distinct_rated_opponents": 65,
          "draws": 128,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "unknown_legacy",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-sonnet-5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "unknown_legacy",
            "request_mode": "unknown_legacy",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-12T16:00:00Z",
          "losses": 36,
          "model": "claude-sonnet-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-259fc4a9e48c81f2",
          "rated_matches": 178,
          "raw_elo_rating": 1387.0397820883597,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 36.3482511329046,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 14
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 90,
          "capped_draws": 14,
          "coverage_status": "rated",
          "distinct_rated_opponents": 42,
          "draws": 14,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "xhigh",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-sonnet-5",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 28,
          "model": "claude-sonnet-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-41b4bf40efe85b59",
          "rated_matches": 90,
          "raw_elo_rating": 1604.7460346224086,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "xhigh",
          "repair_status": "first_pass",
          "score": 57.13530033302503,
          "uncertainty": 8.664241836095918,
          "unilateral_faults": 0,
          "wins": 48
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 102,
          "capped_draws": 18,
          "coverage_status": "rated",
          "distinct_rated_opponents": 50,
          "draws": 18,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "xhigh",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-sonnet-5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-03T16:50:00Z",
          "losses": 34,
          "model": "claude-sonnet-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-5e353d79b07fa294",
          "rated_matches": 102,
          "raw_elo_rating": 1695.23469264125,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "xhigh",
          "repair_status": "first_pass",
          "score": 66.53539430743486,
          "uncertainty": 5.516463908214657,
          "unilateral_faults": 0,
          "wins": 50
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 114,
          "capped_draws": 26,
          "coverage_status": "rated",
          "distinct_rated_opponents": 56,
          "draws": 26,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-sonnet-5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 35,
          "model": "claude-sonnet-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-73ff84eba4ec19cb",
          "rated_matches": 114,
          "raw_elo_rating": 1598.8545648282711,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 57.007926489898445,
          "uncertainty": 2.875240412015687,
          "unilateral_faults": 0,
          "wins": 53
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 89,
          "capped_draws": 16,
          "coverage_status": "rated",
          "distinct_rated_opponents": 42,
          "draws": 16,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-sonnet-5",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 45,
          "model": "claude-sonnet-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-93cff8e6feb76995",
          "rated_matches": 89,
          "raw_elo_rating": 1471.9176789585542,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 43.687018397883946,
          "uncertainty": 8.954627669472988,
          "unilateral_faults": 0,
          "wins": 28
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 98,
          "capped_draws": 10,
          "coverage_status": "rated",
          "distinct_rated_opponents": 47,
          "draws": 10,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-sonnet-5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 39,
          "model": "claude-sonnet-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-cd50a27a6bb44b58",
          "rated_matches": 98,
          "raw_elo_rating": 1525.1532485760156,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 49.265789786658594,
          "uncertainty": 6.501890762960602,
          "unilateral_faults": 0,
          "wins": 49
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 89,
          "capped_draws": 19,
          "coverage_status": "rated",
          "distinct_rated_opponents": 43,
          "draws": 19,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-sonnet-5",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 41,
          "model": "claude-sonnet-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-d1a3c0549627f78e",
          "rated_matches": 89,
          "raw_elo_rating": 1444.200355658939,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 40.88566173777684,
          "uncertainty": 8.954627669472988,
          "unilateral_faults": 0,
          "wins": 29
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 128,
          "capped_draws": 77,
          "coverage_status": "rated",
          "distinct_rated_opponents": 59,
          "draws": 77,
          "evaluated_setting_identity": {
            "canonical_provider_route": "unknown_legacy",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "cohere/north-mini-code:free",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 30,
          "model": "cohere/north-mini-code",
          "point_rating_method": "sequential_elo",
          "public_id": "E-194759b182ce3244",
          "rated_matches": 128,
          "raw_elo_rating": 1489.189872373205,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 46.13468842367974,
          "uncertainty": 0.27254531628119416,
          "unilateral_faults": 0,
          "wins": 21
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 98,
          "capped_draws": 21,
          "coverage_status": "rated",
          "distinct_rated_opponents": 47,
          "draws": 21,
          "evaluated_setting_identity": {
            "canonical_provider_route": "unknown_legacy",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "cohere/north-mini-code:free",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-11T17:22:09Z",
          "losses": 75,
          "model": "cohere/north-mini-code",
          "point_rating_method": "sequential_elo",
          "public_id": "E-c309b463b29efb71",
          "rated_matches": 98,
          "raw_elo_rating": 1037.886145799525,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "none",
          "repair_status": "repaired",
          "score": 0.018287462616778865,
          "uncertainty": 6.501890762960602,
          "unilateral_faults": 0,
          "wins": 2
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 94,
          "capped_draws": 18,
          "coverage_status": "rated",
          "distinct_rated_opponents": 45,
          "draws": 18,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "xhigh",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "deepseek/deepseek-v4-flash",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 51,
          "model": "deepseek/deepseek-v4-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-b9882650a0cde9ac",
          "rated_matches": 94,
          "raw_elo_rating": 1353.1558761739786,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "xhigh",
          "repair_status": "first_pass",
          "score": 31.797564014719292,
          "uncertainty": 7.54891760425771,
          "unilateral_faults": 0,
          "wins": 25
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 76,
          "capped_draws": 26,
          "coverage_status": "rated",
          "distinct_rated_opponents": 38,
          "draws": 26,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "deepseek/deepseek-v4-flash",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T06:10:40Z",
          "losses": 43,
          "model": "deepseek/deepseek-v4-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-f1d9dfb787d0d902",
          "rated_matches": 76,
          "raw_elo_rating": 1160.6408625081874,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "repaired",
          "score": 11.880934761298485,
          "uncertainty": 13.230288229818967,
          "unilateral_faults": 0,
          "wins": 7
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 76,
          "capped_draws": 13,
          "coverage_status": "rated",
          "distinct_rated_opponents": 38,
          "draws": 13,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "deepseek/deepseek-v4-flash",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-01T00:15:48Z",
          "losses": 39,
          "model": "deepseek/deepseek-v4-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-fd9da5310ad15cac",
          "rated_matches": 76,
          "raw_elo_rating": 1561.0748409852954,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 52.35231723983702,
          "uncertainty": 13.230288229818967,
          "unilateral_faults": 0,
          "wins": 24
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 128,
          "capped_draws": 46,
          "coverage_status": "rated",
          "distinct_rated_opponents": 62,
          "draws": 46,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "deepseek/deepseek-v4-pro",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 48,
          "model": "deepseek/deepseek-v4-pro",
          "point_rating_method": "sequential_elo",
          "public_id": "E-e121525dd1846069",
          "rated_matches": 128,
          "raw_elo_rating": 1453.1514954467345,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 42.49233284225822,
          "uncertainty": 0.27254531628119416,
          "unilateral_faults": 0,
          "wins": 34
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 100,
          "capped_draws": 19,
          "coverage_status": "rated",
          "distinct_rated_opponents": 49,
          "draws": 19,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "xhigh",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "deepseek/deepseek-v4-pro",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 48,
          "model": "deepseek/deepseek-v4-pro",
          "point_rating_method": "sequential_elo",
          "public_id": "E-e192048d4eaa3c43",
          "rated_matches": 100,
          "raw_elo_rating": 1453.8732003554912,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "xhigh",
          "repair_status": "repaired",
          "score": 42.10203075533094,
          "uncertainty": 6.001859510499461,
          "unilateral_faults": 0,
          "wins": 33
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 104,
          "capped_draws": 44,
          "coverage_status": "rated",
          "distinct_rated_opponents": 51,
          "draws": 44,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "google/gemini-3.1-flash-lite",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 38,
          "model": "google/gemini-3.1-flash-lite",
          "point_rating_method": "sequential_elo",
          "public_id": "E-7669b8a03ef19548",
          "rated_matches": 104,
          "raw_elo_rating": 1442.0722052107417,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "repaired",
          "score": 40.98668493442913,
          "uncertainty": 5.045003647426665,
          "unilateral_faults": 0,
          "wins": 22
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 76,
          "capped_draws": 25,
          "coverage_status": "rated",
          "distinct_rated_opponents": 38,
          "draws": 25,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "google/gemini-3.1-flash-lite",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 45,
          "model": "google/gemini-3.1-flash-lite",
          "point_rating_method": "sequential_elo",
          "public_id": "E-cc0af0bfa6a9a29f",
          "rated_matches": 76,
          "raw_elo_rating": 1144.1569784358514,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "repaired",
          "score": 10.214928346057336,
          "uncertainty": 13.230288229818967,
          "unilateral_faults": 0,
          "wins": 6
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 90,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 44,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "google/gemini-3.5-flash",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 11,
          "model": "google/gemini-3.5-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-22f31826bcf76511",
          "rated_matches": 88,
          "raw_elo_rating": 1899.4210224251667,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "repaired",
          "score": 86.87039539493097,
          "uncertainty": 9.249894000318006,
          "unilateral_faults": 0,
          "wins": 77
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 0,
          "capped_draws": 0,
          "coverage_status": "pending",
          "distinct_rated_opponents": 0,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "low",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "google/gemini-3.5-flash",
            "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-21T14:20:15Z",
          "losses": 0,
          "model": "google/gemini-3.5-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-b33eea8b864e22bf",
          "rated_matches": 0,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "low",
          "repair_status": "first_pass",
          "unilateral_faults": 0,
          "wins": 0
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 178,
          "capped_draws": 44,
          "coverage_status": "rated",
          "distinct_rated_opponents": 68,
          "draws": 44,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "minimal",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "google/gemini-3.5-flash-lite",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 72,
          "model": "google/gemini-3.5-flash-lite",
          "point_rating_method": "sequential_elo",
          "public_id": "E-21c0edac8ac36f2e",
          "rated_matches": 178,
          "raw_elo_rating": 1370.3859439113394,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "minimal",
          "repair_status": "first_pass",
          "score": 34.66506765991066,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 62
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 144,
          "capped_draws": 24,
          "coverage_status": "rated",
          "distinct_rated_opponents": 52,
          "draws": 24,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "google/gemini-3.5-flash-lite",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 67,
          "model": "google/gemini-3.5-flash-lite",
          "point_rating_method": "sequential_elo",
          "public_id": "E-4b4f303670ce9fb6",
          "rated_matches": 144,
          "raw_elo_rating": 1442.9189216381337,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 41.66026073492735,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 53
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 222,
          "capped_draws": 49,
          "coverage_status": "rated",
          "distinct_rated_opponents": 90,
          "draws": 49,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "google/gemini-3.5-flash-lite",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 88,
          "model": "google/gemini-3.5-flash-lite",
          "point_rating_method": "sequential_elo",
          "public_id": "E-77d8df8cd762fd09",
          "rated_matches": 222,
          "raw_elo_rating": 1407.613568595336,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 38.74208683227142,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 85
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 140,
          "capped_draws": 28,
          "coverage_status": "rated",
          "distinct_rated_opponents": 49,
          "draws": 28,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "google/gemini-3.5-flash-lite",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 78,
          "model": "google/gemini-3.5-flash-lite",
          "point_rating_method": "sequential_elo",
          "public_id": "E-85d9dd9fbf531322",
          "rated_matches": 140,
          "raw_elo_rating": 1318.8398191425192,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "first_pass",
          "score": 29.072445927965525,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 34
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 176,
          "capped_draws": 39,
          "coverage_status": "rated",
          "distinct_rated_opponents": 66,
          "draws": 39,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "minimal",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "google/gemini-3.5-flash-lite",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 88,
          "model": "google/gemini-3.5-flash-lite",
          "point_rating_method": "sequential_elo",
          "public_id": "E-cf51875df5447bc2",
          "rated_matches": 176,
          "raw_elo_rating": 1406.3241755085214,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "minimal",
          "repair_status": "first_pass",
          "score": 38.28027790563501,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 49
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 156,
          "capped_draws": 97,
          "coverage_status": "rated",
          "distinct_rated_opponents": 61,
          "draws": 97,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "google/gemini-3.6-flash",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 33,
          "model": "google/gemini-3.6-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-27590b9ddebe06e6",
          "rated_matches": 156,
          "raw_elo_rating": 1460.350057347287,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 43.552860190190096,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 26
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 100,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 50,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "google/gemini-3.6-flash",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 11,
          "model": "google/gemini-3.6-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-7484f4e7d8863a3b",
          "rated_matches": 100,
          "raw_elo_rating": 1993.5082608374075,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 96.6422998270312,
          "uncertainty": 6.001859510499461,
          "unilateral_faults": 0,
          "wins": 89
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 145,
          "capped_draws": 17,
          "coverage_status": "rated",
          "distinct_rated_opponents": 59,
          "draws": 17,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "google/gemini-3.6-flash",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 39,
          "model": "google/gemini-3.6-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-df0493ecef384a6a",
          "rated_matches": 144,
          "raw_elo_rating": 1710.9348856205506,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "first_pass",
          "score": 68.74831312733114,
          "uncertainty": 0.0,
          "unilateral_faults": 1,
          "wins": 88
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 174,
          "capped_draws": 48,
          "coverage_status": "rated",
          "distinct_rated_opponents": 65,
          "draws": 48,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "minimal",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "google/gemini-3.6-flash",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 92,
          "model": "google/gemini-3.6-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-e0c4f14c94c0a42a",
          "rated_matches": 174,
          "raw_elo_rating": 1192.2933088137934,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "minimal",
          "repair_status": "first_pass",
          "score": 16.631119845397098,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 34
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 178,
          "capped_draws": 75,
          "coverage_status": "rated",
          "distinct_rated_opponents": 67,
          "draws": 75,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "google/gemini-3.6-flash",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 78,
          "model": "google/gemini-3.6-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-e9260a0da3a64563",
          "rated_matches": 178,
          "raw_elo_rating": 1328.4998934490186,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "repaired",
          "score": 30.431694719824712,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 25
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 174,
          "capped_draws": 34,
          "coverage_status": "rated",
          "distinct_rated_opponents": 66,
          "draws": 34,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "minimal",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "google/gemini-3.6-flash",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 94,
          "model": "google/gemini-3.6-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-e9733de94d982ade",
          "rated_matches": 174,
          "raw_elo_rating": 1322.3387367350888,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "minimal",
          "repair_status": "first_pass",
          "score": 29.774655448954377,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 46
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 120,
          "capped_draws": 25,
          "coverage_status": "rated",
          "distinct_rated_opponents": 58,
          "draws": 25,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "google/gemma-4-31b-it",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 40,
          "model": "google/gemma-4-31b-it",
          "point_rating_method": "sequential_elo",
          "public_id": "E-caaa54d3c88e6570",
          "rated_matches": 120,
          "raw_elo_rating": 1453.704251657997,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 42.432414819587265,
          "uncertainty": 1.7045454545454586,
          "unilateral_faults": 0,
          "wins": 55
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 114,
          "capped_draws": 5,
          "coverage_status": "rated",
          "distinct_rated_opponents": 56,
          "draws": 5,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-4.1",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "omitted",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 49,
          "model": "gpt-4.1",
          "point_rating_method": "sequential_elo",
          "public_id": "E-f50ec6b60d5b85da",
          "rated_matches": 113,
          "raw_elo_rating": 1572.9878368669815,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "omitted",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 54.37710879884957,
          "uncertainty": 3.079290579084697,
          "unilateral_faults": 1,
          "wins": 59
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 168,
          "capped_draws": 39,
          "coverage_status": "rated",
          "distinct_rated_opponents": 63,
          "draws": 39,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-4.1-nano",
            "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "omitted",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-12T16:00:00Z",
          "losses": 69,
          "model": "gpt-4.1-nano",
          "point_rating_method": "sequential_elo",
          "public_id": "E-e117cfcfd3d0bf38",
          "rated_matches": 168,
          "raw_elo_rating": 1429.1019623450045,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "omitted",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 40.511310783890416,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 60
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 110,
          "capped_draws": 6,
          "coverage_status": "rated",
          "distinct_rated_opponents": 52,
          "draws": 6,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 54,
          "model": "gpt-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-3e63b136f656e976",
          "rated_matches": 110,
          "raw_elo_rating": 1508.6425409214996,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "first_pass",
          "score": 47.822980600607565,
          "uncertainty": 3.707899787624953,
          "unilateral_faults": 0,
          "wins": 50
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 0,
          "capped_draws": 0,
          "coverage_status": "pending",
          "distinct_rated_opponents": 0,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "low",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5",
            "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-21T14:20:15Z",
          "losses": 0,
          "model": "gpt-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-4370194a9beec334",
          "rated_matches": 0,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "low",
          "repair_status": "first_pass",
          "unilateral_faults": 0,
          "wins": 0
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 94,
          "capped_draws": 17,
          "coverage_status": "rated",
          "distinct_rated_opponents": 45,
          "draws": 17,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 55,
          "model": "gpt-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-adee794ecd761044",
          "rated_matches": 94,
          "raw_elo_rating": 1257.9362460272719,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 22.173830070391556,
          "uncertainty": 7.54891760425771,
          "unilateral_faults": 0,
          "wins": 22
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 86,
          "capped_draws": 19,
          "coverage_status": "rated",
          "distinct_rated_opponents": 42,
          "draws": 19,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.4",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 16,
          "model": "gpt-5.4",
          "point_rating_method": "sequential_elo",
          "public_id": "E-586de6c9939561c3",
          "rated_matches": 84,
          "raw_elo_rating": 1711.1296538562067,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 67.7403406860563,
          "uncertainty": 10.482614454664043,
          "unilateral_faults": 2,
          "wins": 49
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 98,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 47,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "xhigh",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.4",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 5,
          "model": "gpt-5.4",
          "point_rating_method": "sequential_elo",
          "public_id": "E-5d8a6b14c27539ab",
          "rated_matches": 98,
          "raw_elo_rating": 2015.429236982834,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "xhigh",
          "repair_status": "first_pass",
          "score": 98.8173965766658,
          "uncertainty": 6.501890762960602,
          "unilateral_faults": 0,
          "wins": 93
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 102,
          "capped_draws": 2,
          "coverage_status": "rated",
          "distinct_rated_opponents": 48,
          "draws": 2,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.4",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 6,
          "model": "gpt-5.4",
          "point_rating_method": "sequential_elo",
          "public_id": "E-60fa13e461853992",
          "rated_matches": 96,
          "raw_elo_rating": 2013.7931496605154,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 98.61036508816744,
          "uncertainty": 7.017308256680951,
          "unilateral_faults": 0,
          "wins": 88
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 94,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 42,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "xhigh",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.4",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 3,
          "model": "gpt-5.4",
          "point_rating_method": "sequential_elo",
          "public_id": "E-9879a37f54e31cff",
          "rated_matches": 94,
          "raw_elo_rating": 1979.430767061083,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "xhigh",
          "repair_status": "first_pass",
          "score": 95.09441694960572,
          "uncertainty": 7.54891760425771,
          "unilateral_faults": 0,
          "wins": 91
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 94,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 43,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.4",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 1,
          "model": "gpt-5.4",
          "point_rating_method": "sequential_elo",
          "public_id": "E-d4fa7dbb9458c464",
          "rated_matches": 94,
          "raw_elo_rating": 2027.9678324469994,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 100.0,
          "uncertainty": 7.54891760425771,
          "unilateral_faults": 0,
          "wins": 93
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 96,
          "capped_draws": 4,
          "coverage_status": "rated",
          "distinct_rated_opponents": 42,
          "draws": 4,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.4",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 20,
          "model": "gpt-5.4",
          "point_rating_method": "sequential_elo",
          "public_id": "E-ed2ff19b1858f2c4",
          "rated_matches": 96,
          "raw_elo_rating": 1767.2477663915254,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 73.69231856637961,
          "uncertainty": 7.017308256680951,
          "unilateral_faults": 0,
          "wins": 72
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 100,
          "capped_draws": 4,
          "coverage_status": "rated",
          "distinct_rated_opponents": 48,
          "draws": 4,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.4-mini",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 39,
          "model": "gpt-5.4-mini",
          "point_rating_method": "sequential_elo",
          "public_id": "E-62424dfd649cbac9",
          "rated_matches": 98,
          "raw_elo_rating": 1628.750407707507,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 59.73623054906832,
          "uncertainty": 6.501890762960602,
          "unilateral_faults": 2,
          "wins": 55
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 108,
          "capped_draws": 40,
          "coverage_status": "rated",
          "distinct_rated_opponents": 53,
          "draws": 40,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.4-mini",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 46,
          "model": "gpt-5.4-mini",
          "point_rating_method": "sequential_elo",
          "public_id": "E-ea1cb793f92b3cff",
          "rated_matches": 108,
          "raw_elo_rating": 1351.113886438586,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 31.866704468526944,
          "uncertainty": 4.1413142610575715,
          "unilateral_faults": 0,
          "wins": 22
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 108,
          "capped_draws": 22,
          "coverage_status": "rated",
          "distinct_rated_opponents": 52,
          "draws": 22,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.4-nano",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 55,
          "model": "gpt-5.4-nano",
          "point_rating_method": "sequential_elo",
          "public_id": "E-9257cc1e94bf4b17",
          "rated_matches": 108,
          "raw_elo_rating": 1308.066198532366,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 27.51592622364584,
          "uncertainty": 4.1413142610575715,
          "unilateral_faults": 0,
          "wins": 31
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 90,
          "capped_draws": 19,
          "coverage_status": "rated",
          "distinct_rated_opponents": 44,
          "draws": 19,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.4-nano",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-09T17:30:50Z",
          "losses": 24,
          "model": "gpt-5.4-nano",
          "point_rating_method": "sequential_elo",
          "public_id": "E-9eb27042bf28d67c",
          "rated_matches": 90,
          "raw_elo_rating": 1599.004624163251,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 56.55502285621712,
          "uncertainty": 8.664241836095918,
          "unilateral_faults": 0,
          "wins": 47
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 112,
          "capped_draws": 35,
          "coverage_status": "rated",
          "distinct_rated_opponents": 52,
          "draws": 35,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.4-nano",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 38,
          "model": "gpt-5.4-nano",
          "point_rating_method": "sequential_elo",
          "public_id": "E-a8887794a1195b75",
          "rated_matches": 106,
          "raw_elo_rating": 1540.976761634146,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "repaired",
          "score": 51.01989606082149,
          "uncertainty": 4.586824452283178,
          "unilateral_faults": 0,
          "wins": 33
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 82,
          "capped_draws": 4,
          "coverage_status": "rated",
          "distinct_rated_opponents": 40,
          "draws": 4,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.4-nano",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-09T17:30:50Z",
          "losses": 74,
          "model": "gpt-5.4-nano",
          "point_rating_method": "sequential_elo",
          "public_id": "E-c48c1aed1cdecc72",
          "rated_matches": 80,
          "raw_elo_rating": 1041.9481369055254,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "repaired",
          "score": 0.0,
          "uncertainty": 11.805555555555554,
          "unilateral_faults": 2,
          "wins": 2
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 122,
          "capped_draws": 92,
          "coverage_status": "rated",
          "distinct_rated_opponents": 60,
          "draws": 92,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 19,
          "model": "gpt-5.5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-58178b9b32a94ca0",
          "rated_matches": 122,
          "raw_elo_rating": 1507.7226018234821,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 47.92198712859516,
          "uncertainty": 1.3334817333716131,
          "unilateral_faults": 0,
          "wins": 11
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 100,
          "capped_draws": 30,
          "coverage_status": "rated",
          "distinct_rated_opponents": 46,
          "draws": 30,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "xhigh",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 16,
          "model": "gpt-5.5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-8c61292c31db2722",
          "rated_matches": 100,
          "raw_elo_rating": 1756.676617437372,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "xhigh",
          "repair_status": "first_pass",
          "score": 72.70600935658693,
          "uncertainty": 6.001859510499461,
          "unilateral_faults": 0,
          "wins": 54
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 108,
          "capped_draws": 65,
          "coverage_status": "rated",
          "distinct_rated_opponents": 53,
          "draws": 65,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 14,
          "model": "gpt-5.5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-e4496be687faac9d",
          "rated_matches": 108,
          "raw_elo_rating": 1625.1613317167532,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "repaired",
          "score": 59.564351449683706,
          "uncertainty": 4.1413142610575715,
          "unilateral_faults": 0,
          "wins": 29
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 98,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 47,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "xhigh",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.6-luna",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-10T05:30:29Z",
          "losses": 32,
          "model": "gpt-5.6-luna",
          "point_rating_method": "sequential_elo",
          "public_id": "E-38187ed58fb76057",
          "rated_matches": 98,
          "raw_elo_rating": 1832.8760948770332,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "xhigh",
          "repair_status": "first_pass",
          "score": 80.36696920553993,
          "uncertainty": 6.501890762960602,
          "unilateral_faults": 0,
          "wins": 66
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 90,
          "capped_draws": 9,
          "coverage_status": "rated",
          "distinct_rated_opponents": 44,
          "draws": 9,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.6-luna",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-10T05:30:29Z",
          "losses": 29,
          "model": "gpt-5.6-luna",
          "point_rating_method": "sequential_elo",
          "public_id": "E-4f775a5b7b265dae",
          "rated_matches": 90,
          "raw_elo_rating": 1681.7158247375462,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 64.91454480895466,
          "uncertainty": 8.664241836095918,
          "unilateral_faults": 0,
          "wins": 52
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 90,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 42,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "xhigh",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.6-luna",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 20,
          "model": "gpt-5.6-luna",
          "point_rating_method": "sequential_elo",
          "public_id": "E-65def22b992d7636",
          "rated_matches": 90,
          "raw_elo_rating": 1836.192748563626,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "xhigh",
          "repair_status": "first_pass",
          "score": 80.5273424342959,
          "uncertainty": 8.664241836095918,
          "unilateral_faults": 0,
          "wins": 70
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 91,
          "capped_draws": 13,
          "coverage_status": "rated",
          "distinct_rated_opponents": 44,
          "draws": 13,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.6-luna",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 39,
          "model": "gpt-5.6-luna",
          "point_rating_method": "sequential_elo",
          "public_id": "E-87b37ed5ff73def5",
          "rated_matches": 91,
          "raw_elo_rating": 1553.3629268180623,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "repaired",
          "score": 51.96516648339348,
          "uncertainty": 8.378603514268699,
          "unilateral_faults": 0,
          "wins": 39
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 91,
          "capped_draws": 14,
          "coverage_status": "rated",
          "distinct_rated_opponents": 43,
          "draws": 14,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.6-luna",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 68,
          "model": "gpt-5.6-luna",
          "point_rating_method": "sequential_elo",
          "public_id": "E-9502190155453416",
          "rated_matches": 91,
          "raw_elo_rating": 1231.009568848009,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 19.385298777703543,
          "uncertainty": 8.378603514268699,
          "unilateral_faults": 0,
          "wins": 9
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 102,
          "capped_draws": 30,
          "coverage_status": "rated",
          "distinct_rated_opponents": 49,
          "draws": 30,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.6-luna",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-10T05:30:29Z",
          "losses": 55,
          "model": "gpt-5.6-luna",
          "point_rating_method": "sequential_elo",
          "public_id": "E-959ed218b1c5605b",
          "rated_matches": 99,
          "raw_elo_rating": 1231.2408205466734,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 19.58077943551401,
          "uncertainty": 6.25,
          "unilateral_faults": 0,
          "wins": 14
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 92,
          "capped_draws": 21,
          "coverage_status": "rated",
          "distinct_rated_opponents": 42,
          "draws": 21,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.6-sol",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 23,
          "model": "gpt-5.6-sol",
          "point_rating_method": "sequential_elo",
          "public_id": "E-544e51eb5e949386",
          "rated_matches": 92,
          "raw_elo_rating": 1644.1561281370252,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 61.164248353993486,
          "uncertainty": 8.09758473652126,
          "unilateral_faults": 0,
          "wins": 48
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 90,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 42,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.6-sol",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 20,
          "model": "gpt-5.6-sol",
          "point_rating_method": "sequential_elo",
          "public_id": "E-72b9641e74736185",
          "rated_matches": 90,
          "raw_elo_rating": 1820.9424671159038,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 78.9860147584493,
          "uncertainty": 8.664241836095918,
          "unilateral_faults": 0,
          "wins": 70
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 96,
          "capped_draws": 12,
          "coverage_status": "rated",
          "distinct_rated_opponents": 45,
          "draws": 12,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.6-sol",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-10T05:30:29Z",
          "losses": 30,
          "model": "gpt-5.6-sol",
          "point_rating_method": "sequential_elo",
          "public_id": "E-890c38b8e811c121",
          "rated_matches": 90,
          "raw_elo_rating": 1536.020997495056,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 50.18934316422834,
          "uncertainty": 8.664241836095918,
          "unilateral_faults": 0,
          "wins": 48
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 104,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 47,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "xhigh",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.6-sol",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-10T05:30:29Z",
          "losses": 23,
          "model": "gpt-5.6-sol",
          "point_rating_method": "sequential_elo",
          "public_id": "E-9e683b3cd6c7f7c3",
          "rated_matches": 104,
          "raw_elo_rating": 1852.6117511208768,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "xhigh",
          "repair_status": "first_pass",
          "score": 82.47942500679652,
          "uncertainty": 5.045003647426665,
          "unilateral_faults": 0,
          "wins": 81
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 100,
          "capped_draws": 1,
          "coverage_status": "rated",
          "distinct_rated_opponents": 50,
          "draws": 1,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.6-sol",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-10T05:30:29Z",
          "losses": 37,
          "model": "gpt-5.6-sol",
          "point_rating_method": "sequential_elo",
          "public_id": "E-bc834303cebba06a",
          "rated_matches": 100,
          "raw_elo_rating": 1661.0108027125154,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 63.03718007148168,
          "uncertainty": 6.001859510499461,
          "unilateral_faults": 0,
          "wins": 62
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 92,
          "capped_draws": 3,
          "coverage_status": "rated",
          "distinct_rated_opponents": 42,
          "draws": 3,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "xhigh",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.6-sol",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 21,
          "model": "gpt-5.6-sol",
          "point_rating_method": "sequential_elo",
          "public_id": "E-ecb408c0fdea8489",
          "rated_matches": 92,
          "raw_elo_rating": 1743.8724255296063,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "xhigh",
          "repair_status": "first_pass",
          "score": 71.24245506978434,
          "uncertainty": 8.09758473652126,
          "unilateral_faults": 0,
          "wins": 68
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 102,
          "capped_draws": 31,
          "coverage_status": "rated",
          "distinct_rated_opponents": 47,
          "draws": 31,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "xhigh",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.6-terra",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-10T05:30:29Z",
          "losses": 42,
          "model": "gpt-5.6-terra",
          "point_rating_method": "sequential_elo",
          "public_id": "E-36d36f4895d90b11",
          "rated_matches": 102,
          "raw_elo_rating": 1446.6406737765797,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "xhigh",
          "repair_status": "first_pass",
          "score": 41.410294640288974,
          "uncertainty": 5.516463908214657,
          "unilateral_faults": 0,
          "wins": 29
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 98,
          "capped_draws": 30,
          "coverage_status": "rated",
          "distinct_rated_opponents": 48,
          "draws": 30,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.6-terra",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-10T05:30:29Z",
          "losses": 39,
          "model": "gpt-5.6-terra",
          "point_rating_method": "sequential_elo",
          "public_id": "E-40742129939a44b5",
          "rated_matches": 98,
          "raw_elo_rating": 1546.0809635791695,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 51.380928870298845,
          "uncertainty": 6.501890762960602,
          "unilateral_faults": 0,
          "wins": 29
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 98,
          "capped_draws": 34,
          "coverage_status": "rated",
          "distinct_rated_opponents": 47,
          "draws": 34,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.6-terra",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-10T05:30:29Z",
          "losses": 31,
          "model": "gpt-5.6-terra",
          "point_rating_method": "sequential_elo",
          "public_id": "E-46de264ad4571b48",
          "rated_matches": 98,
          "raw_elo_rating": 1468.1014264525709,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "repaired",
          "score": 43.49963047361349,
          "uncertainty": 6.501890762960602,
          "unilateral_faults": 0,
          "wins": 33
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 158,
          "capped_draws": 58,
          "coverage_status": "rated",
          "distinct_rated_opponents": 61,
          "draws": 58,
          "evaluated_setting_identity": {
            "canonical_provider_route": "unknown_legacy",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "inclusionai/ling-3.0-flash:free",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 49,
          "model": "inclusionai/ling-3.0-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-3c618b88b6bdb039",
          "rated_matches": 158,
          "raw_elo_rating": 1323.2806115247317,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 29.719771976725053,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 51
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 32,
          "capped_draws": 8,
          "coverage_status": "rated",
          "distinct_rated_opponents": 15,
          "draws": 8,
          "evaluated_setting_identity": {
            "canonical_provider_route": "unknown_legacy",
            "effective_request_value": "enabled",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "inclusionai/ling-3.0-flash:free",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 19,
          "model": "inclusionai/ling-3.0-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-dd34dd6c69ef6a73",
          "rated_matches": 30,
          "raw_elo_rating": 1343.2896596270887,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "enabled",
          "repair_status": "first_pass",
          "score": 27.68717636213546,
          "uncertainty": 46.05265101338746,
          "unilateral_faults": 0,
          "wins": 3
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 156,
          "capped_draws": 43,
          "coverage_status": "rated",
          "distinct_rated_opponents": 56,
          "draws": 43,
          "evaluated_setting_identity": {
            "canonical_provider_route": "unknown_legacy",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "inclusionai/ling-3.0-flash:free",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 71,
          "model": "inclusionai/ling-3.0-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-f9af396559c3a1cd",
          "rated_matches": 156,
          "raw_elo_rating": 1446.8012623161792,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 42.18349970806349,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 42
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 116,
          "capped_draws": 34,
          "coverage_status": "rated",
          "distinct_rated_opponents": 55,
          "draws": 34,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "meituan/longcat-2.0",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 48,
          "model": "meituan/longcat-2.0",
          "point_rating_method": "sequential_elo",
          "public_id": "E-9f5585b5fd96f2c3",
          "rated_matches": 116,
          "raw_elo_rating": 1389.7867858370455,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 35.91005666671926,
          "uncertainty": 2.4750163521024238,
          "unilateral_faults": 0,
          "wins": 34
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 126,
          "capped_draws": 48,
          "coverage_status": "rated",
          "distinct_rated_opponents": 60,
          "draws": 48,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "meituan/longcat-2.0",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 47,
          "model": "meituan/longcat-2.0",
          "point_rating_method": "sequential_elo",
          "public_id": "E-ed0f8e084958eebc",
          "rated_matches": 126,
          "raw_elo_rating": 1326.9943345633974,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 29.713862088769478,
          "uncertainty": 0.617825470805693,
          "unilateral_faults": 0,
          "wins": 31
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 88,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 42,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "meta/muse-spark-1.2",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-08-13T16:58:34Z",
          "losses": 12,
          "model": "meta/muse-spark-1.2",
          "point_rating_method": "sequential_elo",
          "public_id": "E-052cdf1e5975b860",
          "rated_matches": 88,
          "raw_elo_rating": 1832.923348449229,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 80.14955515143204,
          "uncertainty": 9.249894000318006,
          "unilateral_faults": 0,
          "wins": 76
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 90,
          "capped_draws": 7,
          "coverage_status": "rated",
          "distinct_rated_opponents": 44,
          "draws": 7,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "xhigh",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "meta/muse-spark-1.2",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-08-13T16:58:34Z",
          "losses": 37,
          "model": "meta/muse-spark-1.2",
          "point_rating_method": "sequential_elo",
          "public_id": "E-60e0feec8e72ba89",
          "rated_matches": 90,
          "raw_elo_rating": 1571.9644721957648,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "xhigh",
          "repair_status": "first_pass",
          "score": 53.82210709138648,
          "uncertainty": 8.664241836095918,
          "unilateral_faults": 0,
          "wins": 46
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 92,
          "capped_draws": 39,
          "coverage_status": "rated",
          "distinct_rated_opponents": 43,
          "draws": 39,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "minimal",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "meta/muse-spark-1.2",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-08-13T16:58:34Z",
          "losses": 44,
          "model": "meta/muse-spark-1.2",
          "point_rating_method": "sequential_elo",
          "public_id": "E-d883d9ce56d6c656",
          "rated_matches": 92,
          "raw_elo_rating": 1367.3882021779489,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "minimal",
          "repair_status": "first_pass",
          "score": 33.19164564959547,
          "uncertainty": 8.09758473652126,
          "unilateral_faults": 0,
          "wins": 9
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 124,
          "capped_draws": 24,
          "coverage_status": "rated",
          "distinct_rated_opponents": 61,
          "draws": 24,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "minimax/minimax-m3",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 40,
          "model": "minimax/minimax-m3",
          "point_rating_method": "sequential_elo",
          "public_id": "E-444510032bc433fc",
          "rated_matches": 124,
          "raw_elo_rating": 1518.7090711594628,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 49.061655826617994,
          "uncertainty": 0.9713595499957961,
          "unilateral_faults": 0,
          "wins": 60
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 102,
          "capped_draws": 7,
          "coverage_status": "rated",
          "distinct_rated_opponents": 48,
          "draws": 7,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "enabled",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "minimax/minimax-m3",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 68,
          "model": "minimax/minimax-m3",
          "point_rating_method": "sequential_elo",
          "public_id": "E-e0a841a9daa66219",
          "rated_matches": 102,
          "raw_elo_rating": 1293.2880278495784,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "enabled",
          "repair_status": "repaired",
          "score": 25.911126435305174,
          "uncertainty": 5.516463908214657,
          "unilateral_faults": 0,
          "wins": 27
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 90,
          "capped_draws": 19,
          "coverage_status": "rated",
          "distinct_rated_opponents": 43,
          "draws": 19,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "mistralai/mistral-medium-3-5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 63,
          "model": "mistralai/mistral-medium-3-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-99c7b0d758665b66",
          "rated_matches": 90,
          "raw_elo_rating": 1152.0261703164747,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "first_pass",
          "score": 11.379446013072632,
          "uncertainty": 8.664241836095918,
          "unilateral_faults": 0,
          "wins": 8
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 136,
          "capped_draws": 9,
          "coverage_status": "rated",
          "distinct_rated_opponents": 50,
          "draws": 9,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "mistralai/mistral-medium-3-5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 49,
          "model": "mistralai/mistral-medium-3-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-a0a38f5e77e983bc",
          "rated_matches": 101,
          "raw_elo_rating": 1431.8243444955588,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "repaired",
          "score": 39.8933469399602,
          "uncertainty": 5.757377148833722,
          "unilateral_faults": 35,
          "wins": 43
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 106,
          "capped_draws": 4,
          "coverage_status": "rated",
          "distinct_rated_opponents": 52,
          "draws": 4,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "enabled",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "moonshotai/kimi-k2.7-code",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 51,
          "model": "moonshotai/kimi-k2.7-code",
          "point_rating_method": "sequential_elo",
          "public_id": "E-4935e918b1e70ea1",
          "rated_matches": 106,
          "raw_elo_rating": 1457.399910028884,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "enabled",
          "repair_status": "repaired",
          "score": 42.57288379544755,
          "uncertainty": 4.586824452283178,
          "unilateral_faults": 0,
          "wins": 51
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 145,
          "capped_draws": 16,
          "coverage_status": "rated",
          "distinct_rated_opponents": 54,
          "draws": 16,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "moonshotai/kimi-k3",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T14:00:00Z",
          "losses": 48,
          "model": "moonshotai/kimi-k3",
          "point_rating_method": "sequential_elo",
          "public_id": "E-58aadd759ee9fa72",
          "rated_matches": 136,
          "raw_elo_rating": 1694.6446506662096,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "first_pass",
          "score": 67.00524526280067,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 72
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 174,
          "capped_draws": 17,
          "coverage_status": "rated",
          "distinct_rated_opponents": 69,
          "draws": 17,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "max",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "moonshotai/kimi-k3",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T14:00:00Z",
          "losses": 59,
          "model": "moonshotai/kimi-k3",
          "point_rating_method": "sequential_elo",
          "public_id": "E-dbb89dcf5242a5a0",
          "rated_matches": 174,
          "raw_elo_rating": 1633.9448139210695,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "max",
          "repair_status": "repaired",
          "score": 61.26830836120785,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 98
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 203,
          "capped_draws": 139,
          "coverage_status": "rated",
          "distinct_rated_opponents": 79,
          "draws": 139,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "low",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "moonshotai/kimi-k3",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T14:00:00Z",
          "losses": 32,
          "model": "moonshotai/kimi-k3",
          "point_rating_method": "sequential_elo",
          "public_id": "E-fb8801908d28001f",
          "rated_matches": 203,
          "raw_elo_rating": 1477.9678850754415,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "low",
          "repair_status": "first_pass",
          "score": 45.72944773324043,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 32
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 86,
          "capped_draws": 14,
          "coverage_status": "rated",
          "distinct_rated_opponents": 43,
          "draws": 14,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "nvidia/nemotron-3-ultra-550b-a55b",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 44,
          "model": "nvidia/nemotron-3-ultra-550b-a55b",
          "point_rating_method": "sequential_elo",
          "public_id": "E-0ce5e196701b51f3",
          "rated_matches": 86,
          "raw_elo_rating": 1564.6985011257657,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 52.991414623983445,
          "uncertainty": 9.855626741889738,
          "unilateral_faults": 0,
          "wins": 28
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 96,
          "capped_draws": 20,
          "coverage_status": "rated",
          "distinct_rated_opponents": 47,
          "draws": 20,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "nvidia/nemotron-3-ultra-550b-a55b",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 36,
          "model": "nvidia/nemotron-3-ultra-550b-a55b",
          "point_rating_method": "sequential_elo",
          "public_id": "E-b851008baae8f441",
          "rated_matches": 96,
          "raw_elo_rating": 1528.1057891742366,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "repaired",
          "score": 49.52252542484147,
          "uncertainty": 7.017308256680951,
          "unilateral_faults": 0,
          "wins": 40
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 94,
          "capped_draws": 20,
          "coverage_status": "rated",
          "distinct_rated_opponents": 47,
          "draws": 20,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "nvidia/nemotron-3-ultra-550b-a55b",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-11T17:22:09Z",
          "losses": 52,
          "model": "nvidia/nemotron-3-ultra-550b-a55b",
          "point_rating_method": "sequential_elo",
          "public_id": "E-ce064a9927030b28",
          "rated_matches": 94,
          "raw_elo_rating": 1402.8528152679808,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "repaired",
          "score": 36.82037411124304,
          "uncertainty": 7.54891760425771,
          "unilateral_faults": 0,
          "wins": 22
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 162,
          "capped_draws": 6,
          "coverage_status": "rated",
          "distinct_rated_opponents": 59,
          "draws": 6,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "o3",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-03T15:45:00Z",
          "losses": 50,
          "model": "o3",
          "point_rating_method": "sequential_elo",
          "public_id": "E-01ad69b67b42a9e7",
          "rated_matches": 162,
          "raw_elo_rating": 1645.9887791241347,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "first_pass",
          "score": 62.37508300091857,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 106
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 152,
          "capped_draws": 1,
          "coverage_status": "rated",
          "distinct_rated_opponents": 60,
          "draws": 1,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "o3",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-03T16:00:00Z",
          "losses": 49,
          "model": "o3",
          "point_rating_method": "sequential_elo",
          "public_id": "E-21b0558e9f2190f7",
          "rated_matches": 152,
          "raw_elo_rating": 1713.877626060037,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "first_pass",
          "score": 69.13468390025471,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 102
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 98,
          "capped_draws": 17,
          "coverage_status": "rated",
          "distinct_rated_opponents": 49,
          "draws": 17,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "o3",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 46,
          "model": "o3",
          "point_rating_method": "sequential_elo",
          "public_id": "E-428923c2eb87dc7a",
          "rated_matches": 98,
          "raw_elo_rating": 1468.681575830985,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 43.55826547626181,
          "uncertainty": 6.501890762960602,
          "unilateral_faults": 0,
          "wins": 35
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 132,
          "capped_draws": 25,
          "coverage_status": "rated",
          "distinct_rated_opponents": 50,
          "draws": 25,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "o3",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-03T15:50:00Z",
          "losses": 62,
          "model": "o3",
          "point_rating_method": "sequential_elo",
          "public_id": "E-5e8b87fcfa2225fd",
          "rated_matches": 132,
          "raw_elo_rating": 1412.3908545550473,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "first_pass",
          "score": 38.42663779921314,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 45
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 166,
          "capped_draws": 48,
          "coverage_status": "rated",
          "distinct_rated_opponents": 62,
          "draws": 48,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "low",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "o3",
            "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-21T14:20:15Z",
          "losses": 111,
          "model": "o3",
          "point_rating_method": "sequential_elo",
          "public_id": "E-cb2bd51b4adfa607",
          "rated_matches": 166,
          "raw_elo_rating": 1105.068326196998,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "low",
          "repair_status": "first_pass",
          "score": 7.743053185185025,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 7
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 176,
          "capped_draws": 35,
          "coverage_status": "rated",
          "distinct_rated_opponents": 70,
          "draws": 35,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "low",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "openai/gpt-oss-120b",
            "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-21T14:20:15Z",
          "losses": 113,
          "model": "openai/gpt-oss-120b",
          "point_rating_method": "sequential_elo",
          "public_id": "E-55f6c0e3dc8a8065",
          "rated_matches": 176,
          "raw_elo_rating": 1217.332032382236,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "low",
          "repair_status": "first_pass",
          "score": 19.17906841539228,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 28
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 94,
          "capped_draws": 24,
          "coverage_status": "rated",
          "distinct_rated_opponents": 47,
          "draws": 24,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "openai/gpt-oss-120b",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 43,
          "model": "openai/gpt-oss-120b",
          "point_rating_method": "sequential_elo",
          "public_id": "E-a3e0c8f8ea39b5ec",
          "rated_matches": 94,
          "raw_elo_rating": 1422.8019145344933,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "repaired",
          "score": 38.83660567477785,
          "uncertainty": 7.54891760425771,
          "unilateral_faults": 0,
          "wins": 27
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 122,
          "capped_draws": 20,
          "coverage_status": "rated",
          "distinct_rated_opponents": 60,
          "draws": 20,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "poolside/laguna-s-2.1",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 61,
          "model": "poolside/laguna-s-2.1",
          "point_rating_method": "sequential_elo",
          "public_id": "E-8461eb1b16e40129",
          "rated_matches": 122,
          "raw_elo_rating": 1543.463623200794,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "none",
          "repair_status": "repaired",
          "score": 51.53428934089981,
          "uncertainty": 1.3334817333716131,
          "unilateral_faults": 0,
          "wins": 41
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 118,
          "capped_draws": 34,
          "coverage_status": "rated",
          "distinct_rated_opponents": 56,
          "draws": 34,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "poolside/laguna-s-2.1",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 47,
          "model": "poolside/laguna-s-2.1",
          "point_rating_method": "sequential_elo",
          "public_id": "E-c58ec61528547516",
          "rated_matches": 118,
          "raw_elo_rating": 1410.5416079468907,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 38.039262537272585,
          "uncertainty": 2.084924851410568,
          "unilateral_faults": 0,
          "wins": 37
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 160,
          "capped_draws": 28,
          "coverage_status": "rated",
          "distinct_rated_opponents": 58,
          "draws": 28,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "enabled",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "poolside/laguna-s-2.1",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 74,
          "model": "poolside/laguna-s-2.1",
          "point_rating_method": "sequential_elo",
          "public_id": "E-ffd72d2c5c11728a",
          "rated_matches": 160,
          "raw_elo_rating": 1415.0856930075604,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "enabled",
          "repair_status": "first_pass",
          "score": 39.01837754189059,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 58
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 96,
          "capped_draws": 30,
          "coverage_status": "rated",
          "distinct_rated_opponents": 46,
          "draws": 30,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "enabled",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "qwen/qwen3.7-max",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 54,
          "model": "qwen/qwen3.7-max",
          "point_rating_method": "sequential_elo",
          "public_id": "E-24581eb49b81bf8f",
          "rated_matches": 96,
          "raw_elo_rating": 1196.0815382797539,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "enabled",
          "repair_status": "repaired",
          "score": 15.965232157159793,
          "uncertainty": 7.017308256680951,
          "unilateral_faults": 0,
          "wins": 12
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 106,
          "capped_draws": 27,
          "coverage_status": "rated",
          "distinct_rated_opponents": 50,
          "draws": 27,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "qwen/qwen3.7-max",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 30,
          "model": "qwen/qwen3.7-max",
          "point_rating_method": "sequential_elo",
          "public_id": "E-8a70cd704fcbcf6f",
          "rated_matches": 100,
          "raw_elo_rating": 1573.513576219901,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 54.19394021291321,
          "uncertainty": 6.001859510499461,
          "unilateral_faults": 0,
          "wins": 43
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 100,
          "capped_draws": 18,
          "coverage_status": "rated",
          "distinct_rated_opponents": 49,
          "draws": 18,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "enabled",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "qwen/qwen3.7-plus",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 42,
          "model": "qwen/qwen3.7-plus",
          "point_rating_method": "sequential_elo",
          "public_id": "E-1e5dceaf2ba3ca9a",
          "rated_matches": 100,
          "raw_elo_rating": 1513.515357215152,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "enabled",
          "repair_status": "repaired",
          "score": 48.12999209690405,
          "uncertainty": 6.001859510499461,
          "unilateral_faults": 0,
          "wins": 40
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 100,
          "capped_draws": 26,
          "coverage_status": "rated",
          "distinct_rated_opponents": 49,
          "draws": 26,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "qwen/qwen3.7-plus",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-03T18:55:00Z",
          "losses": 55,
          "model": "qwen/qwen3.7-plus",
          "point_rating_method": "sequential_elo",
          "public_id": "E-5e09f0c994a59f3c",
          "rated_matches": 100,
          "raw_elo_rating": 1300.7914998768108,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "none",
          "repair_status": "repaired",
          "score": 26.630246682212057,
          "uncertainty": 6.001859510499461,
          "unilateral_faults": 0,
          "wins": 19
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 0,
          "capped_draws": 0,
          "coverage_status": "pending",
          "distinct_rated_opponents": 0,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "xhigh",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "qwen/qwen3.8-max",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 0,
          "model": "qwen/qwen3.8-max",
          "point_rating_method": "sequential_elo",
          "public_id": "E-06acc10727220528",
          "rated_matches": 0,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "xhigh",
          "repair_status": "first_pass",
          "unilateral_faults": 0,
          "wins": 0
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 16,
          "capped_draws": 1,
          "coverage_status": "under_covered",
          "distinct_rated_opponents": 9,
          "draws": 1,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "minimal",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "qwen/qwen3.8-max",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 13,
          "model": "qwen/qwen3.8-max",
          "point_rating_method": "sequential_elo",
          "public_id": "E-60f1c4442483d5b0",
          "rated_matches": 16,
          "raw_elo_rating": 1364.0547383269693,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "minimal",
          "repair_status": "first_pass",
          "score": 27.24176104741712,
          "uncertainty": 77.5178125181665,
          "unilateral_faults": 0,
          "wins": 2
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 16,
          "capped_draws": 5,
          "coverage_status": "under_covered",
          "distinct_rated_opponents": 10,
          "draws": 5,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "qwen/qwen3.8-max",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 4,
          "model": "qwen/qwen3.8-max",
          "point_rating_method": "sequential_elo",
          "public_id": "E-ef3bbb2ff5470c0f",
          "rated_matches": 16,
          "raw_elo_rating": 1500.3453591301432,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 41.01649081370751,
          "uncertainty": 77.5178125181665,
          "unilateral_faults": 0,
          "wins": 7
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 14,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 7,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "max",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "stealth/ox-alpha",
            "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-08-22T00:27:26Z",
          "losses": 1,
          "model": "stealth/ox-alpha",
          "point_rating_method": "sequential_elo",
          "public_id": "E-3869622aa388e835",
          "rated_matches": 14,
          "raw_elo_rating": 1643.1131365588276,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "max",
          "repair_status": "first_pass",
          "score": 54.81263208060843,
          "uncertainty": 85.34944487358055,
          "unilateral_faults": 0,
          "wins": 13
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 14,
          "capped_draws": 2,
          "coverage_status": "rated",
          "distinct_rated_opponents": 7,
          "draws": 2,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "low",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "stealth/ox-alpha",
            "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-08-22T00:27:26Z",
          "losses": 4,
          "model": "stealth/ox-alpha",
          "point_rating_method": "sequential_elo",
          "public_id": "E-5661caf556b12391",
          "rated_matches": 14,
          "raw_elo_rating": 1544.9909685045918,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "low",
          "repair_status": "repaired",
          "score": 44.89554210725235,
          "uncertainty": 85.34944487358055,
          "unilateral_faults": 0,
          "wins": 8
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 14,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 7,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "low",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "stealth/ox-alpha",
            "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-08-22T00:27:26Z",
          "losses": 12,
          "model": "stealth/ox-alpha",
          "point_rating_method": "sequential_elo",
          "public_id": "E-98157b387f582b30",
          "rated_matches": 14,
          "raw_elo_rating": 1375.4345756977473,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "low",
          "repair_status": "repaired",
          "score": 27.758680617463924,
          "uncertainty": 85.34944487358055,
          "unilateral_faults": 0,
          "wins": 2
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 14,
          "capped_draws": 2,
          "coverage_status": "rated",
          "distinct_rated_opponents": 7,
          "draws": 2,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "stealth/ox-alpha",
            "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-08-22T00:27:26Z",
          "losses": 2,
          "model": "stealth/ox-alpha",
          "point_rating_method": "sequential_elo",
          "public_id": "E-c6a1445bccefbe07",
          "rated_matches": 14,
          "raw_elo_rating": 1586.795907182653,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "repaired",
          "score": 49.120717176476376,
          "uncertainty": 85.34944487358055,
          "unilateral_faults": 0,
          "wins": 10
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 14,
          "capped_draws": 1,
          "coverage_status": "rated",
          "distinct_rated_opponents": 7,
          "draws": 1,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "stealth/ox-alpha",
            "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-08-22T00:27:26Z",
          "losses": 8,
          "model": "stealth/ox-alpha",
          "point_rating_method": "sequential_elo",
          "public_id": "E-d28e485f395cbca4",
          "rated_matches": 14,
          "raw_elo_rating": 1474.0444126130988,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "first_pass",
          "score": 37.72505869837807,
          "uncertainty": 85.34944487358055,
          "unilateral_faults": 0,
          "wins": 5
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 14,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 7,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "max",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "stealth/ox-alpha",
            "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-08-22T00:27:26Z",
          "losses": 9,
          "model": "stealth/ox-alpha",
          "point_rating_method": "sequential_elo",
          "public_id": "E-dc2b7cd047c7694a",
          "rated_matches": 14,
          "raw_elo_rating": 1448.9187433283219,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "max",
          "repair_status": "first_pass",
          "score": 35.18563740470879,
          "uncertainty": 85.34944487358055,
          "unilateral_faults": 0,
          "wins": 5
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 14,
          "capped_draws": 1,
          "coverage_status": "rated",
          "distinct_rated_opponents": 7,
          "draws": 1,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "low",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "stealth/ox-alpha",
            "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-08-22T00:27:26Z",
          "losses": 11,
          "model": "stealth/ox-alpha",
          "point_rating_method": "sequential_elo",
          "public_id": "E-e66ff5a9cbd5132f",
          "rated_matches": 14,
          "raw_elo_rating": 1396.0549803844092,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "low",
          "repair_status": "first_pass",
          "score": 29.842760215578874,
          "uncertainty": 85.34944487358055,
          "unilateral_faults": 0,
          "wins": 2
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 14,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 7,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "max",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "stealth/ox-alpha",
            "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-08-22T00:27:26Z",
          "losses": 6,
          "model": "stealth/ox-alpha",
          "point_rating_method": "sequential_elo",
          "public_id": "E-e70cadce2bb0e8b1",
          "rated_matches": 14,
          "raw_elo_rating": 1530.6472757303504,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "max",
          "repair_status": "first_pass",
          "score": 43.445842262527115,
          "uncertainty": 85.34944487358055,
          "unilateral_faults": 0,
          "wins": 8
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 82,
          "capped_draws": 6,
          "coverage_status": "rated",
          "distinct_rated_opponents": 41,
          "draws": 6,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "stepfun/step-3.7-flash",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 62,
          "model": "stepfun/step-3.7-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-4b0ce2bc67b08d8a",
          "rated_matches": 82,
          "raw_elo_rating": 1165.3075653397077,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "repaired",
          "score": 12.522239497043625,
          "uncertainty": 11.132129994845172,
          "unilateral_faults": 0,
          "wins": 14
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 102,
          "capped_draws": 18,
          "coverage_status": "rated",
          "distinct_rated_opponents": 51,
          "draws": 18,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "tencent/hy3-preview",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 39,
          "model": "tencent/hy3-preview",
          "point_rating_method": "sequential_elo",
          "public_id": "E-29e8870e43d717e5",
          "rated_matches": 102,
          "raw_elo_rating": 1614.8727554112447,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "first_pass",
          "score": 58.41330958645064,
          "uncertainty": 5.516463908214657,
          "unilateral_faults": 0,
          "wins": 45
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 106,
          "capped_draws": 18,
          "coverage_status": "rated",
          "distinct_rated_opponents": 50,
          "draws": 18,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "tencent/hy3-preview",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 19,
          "model": "tencent/hy3-preview",
          "point_rating_method": "sequential_elo",
          "public_id": "E-3407ff2dd1928eb5",
          "rated_matches": 100,
          "raw_elo_rating": 1740.5175222083988,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 71.07282896064237,
          "uncertainty": 6.001859510499461,
          "unilateral_faults": 0,
          "wins": 63
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 138,
          "capped_draws": 35,
          "coverage_status": "rated",
          "distinct_rated_opponents": 52,
          "draws": 35,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "thinkingmachines/inkling",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 76,
          "model": "thinkingmachines/inkling",
          "point_rating_method": "sequential_elo",
          "public_id": "E-46c7f693daaae605",
          "rated_matches": 138,
          "raw_elo_rating": 1359.3433979275337,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 33.14168798272348,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 27
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 116,
          "capped_draws": 51,
          "coverage_status": "rated",
          "distinct_rated_opponents": 55,
          "draws": 51,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "thinkingmachines/inkling",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 49,
          "model": "thinkingmachines/inkling",
          "point_rating_method": "sequential_elo",
          "public_id": "E-9e638fc0ac98df4f",
          "rated_matches": 116,
          "raw_elo_rating": 1225.1596954073368,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 19.271393862806924,
          "uncertainty": 2.4750163521024238,
          "unilateral_faults": 0,
          "wins": 16
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 142,
          "capped_draws": 53,
          "coverage_status": "rated",
          "distinct_rated_opponents": 50,
          "draws": 53,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "max",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "thinkingmachines/inkling",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 83,
          "model": "thinkingmachines/inkling",
          "point_rating_method": "sequential_elo",
          "public_id": "E-ab1de1dc51400446",
          "rated_matches": 142,
          "raw_elo_rating": 1200.6961116510595,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "max",
          "repair_status": "first_pass",
          "score": 17.155695255029734,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 6
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 114,
          "capped_draws": 33,
          "coverage_status": "rated",
          "distinct_rated_opponents": 54,
          "draws": 33,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "thinkingmachines/inkling",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 75,
          "model": "thinkingmachines/inkling",
          "point_rating_method": "sequential_elo",
          "public_id": "E-bc7c657b08ebac66",
          "rated_matches": 114,
          "raw_elo_rating": 1093.3154458051438,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 5.913693373969095,
          "uncertainty": 2.875240412015687,
          "unilateral_faults": 0,
          "wins": 6
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 0,
          "capped_draws": 0,
          "coverage_status": "pending",
          "distinct_rated_opponents": 0,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "max",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "thinkingmachines/inkling-small",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 0,
          "model": "thinkingmachines/inkling-small",
          "point_rating_method": "sequential_elo",
          "public_id": "E-40197ff2c5984de1",
          "rated_matches": 0,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "max",
          "repair_status": "first_pass",
          "unilateral_faults": 0,
          "wins": 0
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 19,
          "capped_draws": 3,
          "coverage_status": "under_covered",
          "distinct_rated_opponents": 9,
          "draws": 3,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "thinkingmachines/inkling-small",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 7,
          "model": "thinkingmachines/inkling-small",
          "point_rating_method": "sequential_elo",
          "public_id": "E-52cb66309e46f2f3",
          "rated_matches": 19,
          "raw_elo_rating": 1494.0445342877708,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 41.144919554096006,
          "uncertainty": 68.05339887498948,
          "unilateral_faults": 0,
          "wins": 9
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 20,
          "capped_draws": 3,
          "coverage_status": "under_covered",
          "distinct_rated_opponents": 9,
          "draws": 3,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "thinkingmachines/inkling-small",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 15,
          "model": "thinkingmachines/inkling-small",
          "point_rating_method": "sequential_elo",
          "public_id": "E-53de0c492cdf9f2f",
          "rated_matches": 20,
          "raw_elo_rating": 1346.7122318417303,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 26.47208042284504,
          "uncertainty": 65.3589451179962,
          "unilateral_faults": 0,
          "wins": 2
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 170,
          "capped_draws": 32,
          "coverage_status": "rated",
          "distinct_rated_opponents": 66,
          "draws": 32,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "x-ai/grok-4.5",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T14:00:00Z",
          "losses": 19,
          "model": "x-ai/grok-4.5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-1c8e452ede41ea2e",
          "rated_matches": 170,
          "raw_elo_rating": 1829.172240589223,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "repaired",
          "score": 80.96417402361442,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 119
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 209,
          "capped_draws": 134,
          "coverage_status": "rated",
          "distinct_rated_opponents": 80,
          "draws": 134,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "low",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "x-ai/grok-4.5",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T14:00:00Z",
          "losses": 36,
          "model": "x-ai/grok-4.5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-7ee1b68d1249ac22",
          "rated_matches": 209,
          "raw_elo_rating": 1475.140841118312,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "low",
          "repair_status": "first_pass",
          "score": 45.4844504231055,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 39
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 104,
          "capped_draws": 8,
          "coverage_status": "rated",
          "distinct_rated_opponents": 51,
          "draws": 8,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "x-ai/grok-4.5",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T14:00:00Z",
          "losses": 21,
          "model": "x-ai/grok-4.5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-d709aeb6802f9289",
          "rated_matches": 102,
          "raw_elo_rating": 1777.1699941075071,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 74.81649706686221,
          "uncertainty": 5.516463908214657,
          "unilateral_faults": 2,
          "wins": 73
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 108,
          "capped_draws": 23,
          "coverage_status": "rated",
          "distinct_rated_opponents": 49,
          "draws": 23,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "enabled",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "x-ai/grok-build-0.1",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 43,
          "model": "x-ai/grok-build-0.1",
          "point_rating_method": "sequential_elo",
          "public_id": "E-f1ded648f3ab17dc",
          "rated_matches": 108,
          "raw_elo_rating": 1483.761287066289,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "enabled",
          "repair_status": "repaired",
          "score": 45.273218336317015,
          "uncertainty": 4.1413142610575715,
          "unilateral_faults": 0,
          "wins": 42
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 110,
          "capped_draws": 3,
          "coverage_status": "rated",
          "distinct_rated_opponents": 50,
          "draws": 3,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "enabled",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "xiaomi/mimo-v2.5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 60,
          "model": "xiaomi/mimo-v2.5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-1208f50b0908ecb4",
          "rated_matches": 110,
          "raw_elo_rating": 1280.781906067578,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "enabled",
          "repair_status": "repaired",
          "score": 24.79337921651107,
          "uncertainty": 3.707899787624953,
          "unilateral_faults": 0,
          "wins": 47
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 102,
          "capped_draws": 16,
          "coverage_status": "rated",
          "distinct_rated_opponents": 48,
          "draws": 16,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "xiaomi/mimo-v2.5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T06:10:40Z",
          "losses": 56,
          "model": "xiaomi/mimo-v2.5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-2a71bee21bd7c0b9",
          "rated_matches": 102,
          "raw_elo_rating": 1405.5069647830076,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "repaired",
          "score": 37.25295995113266,
          "uncertainty": 5.516463908214657,
          "unilateral_faults": 0,
          "wins": 30
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 94,
          "capped_draws": 7,
          "coverage_status": "rated",
          "distinct_rated_opponents": 47,
          "draws": 7,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "xiaomi/mimo-v2.5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T06:10:40Z",
          "losses": 40,
          "model": "xiaomi/mimo-v2.5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-2cdd8ae895784956",
          "rated_matches": 94,
          "raw_elo_rating": 1599.2443785426199,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 56.66943413125931,
          "uncertainty": 7.54891760425771,
          "unilateral_faults": 0,
          "wins": 47
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 72,
          "capped_draws": 41,
          "coverage_status": "rated",
          "distinct_rated_opponents": 36,
          "draws": 41,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "xiaomi/mimo-v2.5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T06:10:40Z",
          "losses": 29,
          "model": "xiaomi/mimo-v2.5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-8478c64d84536b61",
          "rated_matches": 72,
          "raw_elo_rating": 1213.1687467409479,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "repaired",
          "score": 17.065325253973946,
          "uncertainty": 14.770573598065289,
          "unilateral_faults": 0,
          "wins": 2
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 120,
          "capped_draws": 27,
          "coverage_status": "rated",
          "distinct_rated_opponents": 59,
          "draws": 27,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "xiaomi/mimo-v2.5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 51,
          "model": "xiaomi/mimo-v2.5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-912a4a40bbdcbd45",
          "rated_matches": 120,
          "raw_elo_rating": 1488.5178228047191,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 45.95098074818603,
          "uncertainty": 1.7045454545454586,
          "unilateral_faults": 0,
          "wins": 42
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 100,
          "capped_draws": 29,
          "coverage_status": "rated",
          "distinct_rated_opponents": 50,
          "draws": 29,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "xiaomi/mimo-v2.5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-01T00:15:48Z",
          "losses": 43,
          "model": "xiaomi/mimo-v2.5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-a168350bd057f924",
          "rated_matches": 100,
          "raw_elo_rating": 1398.495256527627,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 36.50504831628788,
          "uncertainty": 6.001859510499461,
          "unilateral_faults": 0,
          "wins": 28
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 116,
          "capped_draws": 32,
          "coverage_status": "rated",
          "distinct_rated_opponents": 57,
          "draws": 32,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "xiaomi/mimo-v2.5-pro",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 51,
          "model": "xiaomi/mimo-v2.5-pro",
          "point_rating_method": "sequential_elo",
          "public_id": "E-9ce4191c7f1f3b3e",
          "rated_matches": 116,
          "raw_elo_rating": 1402.395743836614,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 37.18442894600758,
          "uncertainty": 2.4750163521024238,
          "unilateral_faults": 0,
          "wins": 33
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 82,
          "capped_draws": 26,
          "coverage_status": "rated",
          "distinct_rated_opponents": 41,
          "draws": 26,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "z-ai/glm-5.2",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-11T14:00:45Z",
          "losses": 27,
          "model": "z-ai/glm-5.2",
          "point_rating_method": "sequential_elo",
          "public_id": "E-5c3b7f5666a38043",
          "rated_matches": 82,
          "raw_elo_rating": 1449.4233859714943,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 41.23748511312021,
          "uncertainty": 11.132129994845172,
          "unilateral_faults": 0,
          "wins": 29
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 74,
          "capped_draws": 3,
          "coverage_status": "rated",
          "distinct_rated_opponents": 37,
          "draws": 3,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "z-ai/glm-5.2",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 49,
          "model": "z-ai/glm-5.2",
          "point_rating_method": "sequential_elo",
          "public_id": "E-c8076ea61de8da45",
          "rated_matches": 74,
          "raw_elo_rating": 1201.6984567131585,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 15.969552191859187,
          "uncertainty": 13.985026918962571,
          "unilateral_faults": 0,
          "wins": 22
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 80,
          "capped_draws": 7,
          "coverage_status": "rated",
          "distinct_rated_opponents": 40,
          "draws": 7,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "z-ai/glm-5.2",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-11T17:22:09Z",
          "losses": 30,
          "model": "z-ai/glm-5.2",
          "point_rating_method": "sequential_elo",
          "public_id": "E-f889d782e3cce209",
          "rated_matches": 80,
          "raw_elo_rating": 1437.7540280999642,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "repaired",
          "score": 40.0036272413998,
          "uncertainty": 11.805555555555554,
          "unilateral_faults": 0,
          "wins": 43
        }
      ],
      "GB2-02": [
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 80,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 37,
          "draws": 31,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-fable-5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 9,
          "model": "claude-fable-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-cd3608270e8c00fd",
          "rated_matches": 78,
          "raw_elo_rating": 1685.6539281264988,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 68.84186917568367,
          "uncertainty": 12.5043950463012,
          "unilateral_faults": 2,
          "wins": 38
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 84,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 37,
          "draws": 37,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "xhigh",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-fable-5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-03T17:50:00Z",
          "losses": 4,
          "model": "claude-fable-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-f6a30e7d9986c9b8",
          "rated_matches": 84,
          "raw_elo_rating": 1705.9057480073943,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "xhigh",
          "repair_status": "first_pass",
          "score": 73.74954635252826,
          "uncertainty": 10.482614454664043,
          "unilateral_faults": 0,
          "wins": 43
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 138,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 54,
          "draws": 125,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-opus-4-5",
            "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 11,
          "model": "claude-opus-4-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-03472a04778e9928",
          "rated_matches": 138,
          "raw_elo_rating": 1466.4846616121374,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 22.143649514386354,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 2
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 0,
          "capped_draws": 0,
          "coverage_status": "pending",
          "distinct_rated_opponents": 0,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "legacy_shared_thinking_budget",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-opus-4-5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "budget",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 0,
          "model": "claude-opus-4-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-0454dbb9530f84f7",
          "rated_matches": 0,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "budget",
          "reasoning_setting": "legacy_shared_thinking_budget",
          "repair_status": "first_pass",
          "unilateral_faults": 0,
          "wins": 0
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 94,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 47,
          "draws": 78,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-opus-4-5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "omitted",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 11,
          "model": "claude-opus-4-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-16462f3d1f3a7b19",
          "rated_matches": 94,
          "raw_elo_rating": 1488.645381413465,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "omitted",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 25.52082770903801,
          "uncertainty": 7.54891760425771,
          "unilateral_faults": 0,
          "wins": 5
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 0,
          "capped_draws": 0,
          "coverage_status": "pending",
          "distinct_rated_opponents": 0,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "legacy_shared_thinking_budget",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-opus-4-5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "budget",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 0,
          "model": "claude-opus-4-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-3cbd11fb314c75e1",
          "rated_matches": 0,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "budget",
          "reasoning_setting": "legacy_shared_thinking_budget",
          "repair_status": "first_pass",
          "unilateral_faults": 0,
          "wins": 0
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 130,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 50,
          "draws": 107,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-opus-4-5",
            "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 22,
          "model": "claude-opus-4-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-63fde27ceab11930",
          "rated_matches": 130,
          "raw_elo_rating": 1428.2065730933373,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "first_pass",
          "score": 13.32462959183295,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 1
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 86,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 36,
          "draws": 32,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "xhigh",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-opus-4-8",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-03T17:20:00Z",
          "losses": 5,
          "model": "claude-opus-4-8",
          "point_rating_method": "sequential_elo",
          "public_id": "E-a81bd03e764818f6",
          "rated_matches": 86,
          "raw_elo_rating": 1739.7423942603561,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "xhigh",
          "repair_status": "first_pass",
          "score": 81.45539006883097,
          "uncertainty": 9.855626741889738,
          "unilateral_faults": 0,
          "wins": 49
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 76,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 37,
          "draws": 68,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-opus-4-8",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "omitted",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 5,
          "model": "claude-opus-4-8",
          "point_rating_method": "sequential_elo",
          "public_id": "E-c142942f4138c871",
          "rated_matches": 76,
          "raw_elo_rating": 1462.7697346783725,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "omitted",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 18.694108648166214,
          "uncertainty": 13.230288229818967,
          "unilateral_faults": 0,
          "wins": 3
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 78,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 39,
          "draws": 72,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-opus-4-8",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 5,
          "model": "claude-opus-4-8",
          "point_rating_method": "sequential_elo",
          "public_id": "E-ed71c4ecf219b609",
          "rated_matches": 78,
          "raw_elo_rating": 1451.7183503047993,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 16.344385607773184,
          "uncertainty": 12.5043950463012,
          "unilateral_faults": 0,
          "wins": 1
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 76,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 38,
          "draws": 32,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-opus-5",
            "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-25T10:50:00Z",
          "losses": 9,
          "model": "claude-opus-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-50b401cafe71e710",
          "rated_matches": 76,
          "raw_elo_rating": 1657.8362240629167,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 62.46897998868618,
          "uncertainty": 13.230288229818967,
          "unilateral_faults": 0,
          "wins": 35
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 94,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 47,
          "draws": 26,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-opus-5",
            "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-25T10:50:00Z",
          "losses": 10,
          "model": "claude-opus-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-51ddad48e10b006f",
          "rated_matches": 94,
          "raw_elo_rating": 1672.997271856207,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 66.89123587588573,
          "uncertainty": 7.54891760425771,
          "unilateral_faults": 0,
          "wins": 58
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 58,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 22,
          "draws": 25,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "xhigh",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-opus-5",
            "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-25T15:48:01Z",
          "losses": 10,
          "model": "claude-opus-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-6b45cf5aebf0c66e",
          "rated_matches": 58,
          "raw_elo_rating": 1643.2395344365823,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "xhigh",
          "repair_status": "first_pass",
          "score": 57.73661660019647,
          "uncertainty": 21.344455490411935,
          "unilateral_faults": 0,
          "wins": 23
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 92,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 46,
          "draws": 50,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-opus-5",
            "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-25T10:50:00Z",
          "losses": 4,
          "model": "claude-opus-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-772d1a710082ddb3",
          "rated_matches": 92,
          "raw_elo_rating": 1635.8038282071802,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 58.44615398538018,
          "uncertainty": 8.09758473652126,
          "unilateral_faults": 0,
          "wins": 38
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 76,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 38,
          "draws": 36,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-opus-5",
            "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-25T10:50:00Z",
          "losses": 7,
          "model": "claude-opus-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-8a5bf2e23121edf6",
          "rated_matches": 76,
          "raw_elo_rating": 1647.1115742963248,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 60.0622613093993,
          "uncertainty": 13.230288229818967,
          "unilateral_faults": 0,
          "wins": 33
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 60,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 23,
          "draws": 13,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "xhigh",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-opus-5",
            "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-25T15:48:01Z",
          "losses": 11,
          "model": "claude-opus-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-fcdd98d74e80134a",
          "rated_matches": 60,
          "raw_elo_rating": 1754.756883936148,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "xhigh",
          "repair_status": "first_pass",
          "score": 82.95540018008184,
          "uncertainty": 20.268439966447993,
          "unilateral_faults": 0,
          "wins": 36
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 62,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 30,
          "draws": 55,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-sonnet-5",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 3,
          "model": "claude-sonnet-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-874db7679e1f7332",
          "rated_matches": 62,
          "raw_elo_rating": 1511.2971744001827,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 28.504507698976763,
          "uncertainty": 19.244078834871203,
          "unilateral_faults": 0,
          "wins": 4
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 78,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 36,
          "draws": 73,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-sonnet-5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 4,
          "model": "claude-sonnet-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-a1a16bb5799cfdbe",
          "rated_matches": 78,
          "raw_elo_rating": 1476.5961079238732,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 21.927203253446606,
          "uncertainty": 12.5043950463012,
          "unilateral_faults": 0,
          "wins": 1
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 70,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 32,
          "draws": 61,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-sonnet-5",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 8,
          "model": "claude-sonnet-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-b46bdcad35bcea1d",
          "rated_matches": 70,
          "raw_elo_rating": 1463.6081174048713,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 18.458780422070696,
          "uncertainty": 15.58908290969266,
          "unilateral_faults": 0,
          "wins": 1
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 68,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 30,
          "draws": 62,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "xhigh",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-sonnet-5",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 5,
          "model": "claude-sonnet-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-d4d2fc700a2c74f1",
          "rated_matches": 68,
          "raw_elo_rating": 1463.1243014745253,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "xhigh",
          "repair_status": "first_pass",
          "score": 18.196918446623908,
          "uncertainty": 16.4429265428846,
          "unilateral_faults": 0,
          "wins": 1
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 82,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 38,
          "draws": 55,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "xhigh",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-sonnet-5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-03T16:50:00Z",
          "losses": 15,
          "model": "claude-sonnet-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-e35d82f3fd09a1f4",
          "rated_matches": 82,
          "raw_elo_rating": 1511.6295667779777,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "xhigh",
          "repair_status": "first_pass",
          "score": 30.035421839838055,
          "uncertainty": 11.132129994845172,
          "unilateral_faults": 0,
          "wins": 12
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 94,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 47,
          "draws": 81,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-sonnet-5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 10,
          "model": "claude-sonnet-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-e501d6808bd19ccc",
          "rated_matches": 94,
          "raw_elo_rating": 1480.840389816271,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 23.76930952639686,
          "uncertainty": 7.54891760425771,
          "unilateral_faults": 0,
          "wins": 3
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 66,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 33,
          "draws": 55,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "deepseek/deepseek-v4-flash",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T06:10:40Z",
          "losses": 11,
          "model": "deepseek/deepseek-v4-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-08e2baea96c43eb4",
          "rated_matches": 66,
          "raw_elo_rating": 1431.814073892673,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 11.010487913026688,
          "uncertainty": 17.33472217815261,
          "unilateral_faults": 0,
          "wins": 0
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 74,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 36,
          "draws": 59,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "xhigh",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "deepseek/deepseek-v4-flash",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 11,
          "model": "deepseek/deepseek-v4-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-12dcb25370550495",
          "rated_matches": 74,
          "raw_elo_rating": 1479.442621444907,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "xhigh",
          "repair_status": "repaired",
          "score": 22.300174477766653,
          "uncertainty": 13.985026918962571,
          "unilateral_faults": 0,
          "wins": 4
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 70,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 35,
          "draws": 59,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "deepseek/deepseek-v4-flash",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-01T00:15:48Z",
          "losses": 9,
          "model": "deepseek/deepseek-v4-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-1e168b9e73c26073",
          "rated_matches": 70,
          "raw_elo_rating": 1483.118399769498,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "repaired",
          "score": 22.83708293329852,
          "uncertainty": 15.58908290969266,
          "unilateral_faults": 0,
          "wins": 2
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 84,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 42,
          "draws": 80,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "deepseek/deepseek-v4-flash",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 3,
          "model": "deepseek/deepseek-v4-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-3358fbcda6ab6f4d",
          "rated_matches": 84,
          "raw_elo_rating": 1462.6834789339953,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 19.168036379032152,
          "uncertainty": 10.482614454664043,
          "unilateral_faults": 0,
          "wins": 1
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 88,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 44,
          "draws": 80,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "deepseek/deepseek-v4-pro",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 6,
          "model": "deepseek/deepseek-v4-pro",
          "point_rating_method": "sequential_elo",
          "public_id": "E-6c3b019c1b20a09b",
          "rated_matches": 88,
          "raw_elo_rating": 1473.8446177830178,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 21.894015414373516,
          "uncertainty": 9.249894000318006,
          "unilateral_faults": 0,
          "wins": 2
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 62,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 31,
          "draws": 59,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "google/gemini-3.1-flash-lite",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 2,
          "model": "google/gemini-3.1-flash-lite",
          "point_rating_method": "sequential_elo",
          "public_id": "E-20b3484be872df52",
          "rated_matches": 62,
          "raw_elo_rating": 1477.5240632772964,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "repaired",
          "score": 20.925483752639348,
          "uncertainty": 19.244078834871203,
          "unilateral_faults": 0,
          "wins": 1
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 94,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 47,
          "draws": 74,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "google/gemini-3.5-flash",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 10,
          "model": "google/gemini-3.5-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-ef7a835bdb46a90e",
          "rated_matches": 94,
          "raw_elo_rating": 1490.007826929545,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "repaired",
          "score": 25.82657411049858,
          "uncertainty": 7.54891760425771,
          "unilateral_faults": 0,
          "wins": 10
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 126,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 48,
          "draws": 112,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "minimal",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "google/gemini-3.5-flash-lite",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 12,
          "model": "google/gemini-3.5-flash-lite",
          "point_rating_method": "sequential_elo",
          "public_id": "E-1010911d64a09b68",
          "rated_matches": 126,
          "raw_elo_rating": 1459.4460310730938,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "minimal",
          "repair_status": "repaired",
          "score": 20.212526552183117,
          "uncertainty": 0.617825470805693,
          "unilateral_faults": 0,
          "wins": 2
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 100,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 38,
          "draws": 81,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "google/gemini-3.5-flash-lite",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 8,
          "model": "google/gemini-3.5-flash-lite",
          "point_rating_method": "sequential_elo",
          "public_id": "E-423f6c31467b8943",
          "rated_matches": 100,
          "raw_elo_rating": 1493.463385992254,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "first_pass",
          "score": 26.879776376230204,
          "uncertainty": 6.001859510499461,
          "unilateral_faults": 0,
          "wins": 11
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 107,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 41,
          "draws": 105,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "google/gemini-3.5-flash-lite",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 2,
          "model": "google/gemini-3.5-flash-lite",
          "point_rating_method": "sequential_elo",
          "public_id": "E-dbbc5835674b5f2c",
          "rated_matches": 107,
          "raw_elo_rating": 1472.044979547752,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 22.367578645782174,
          "uncertainty": 4.362522432468809,
          "unilateral_faults": 0,
          "wins": 0
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 130,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 49,
          "draws": 122,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "minimal",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "google/gemini-3.5-flash-lite",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 8,
          "model": "google/gemini-3.5-flash-lite",
          "point_rating_method": "sequential_elo",
          "public_id": "E-e65fdcb71f09a611",
          "rated_matches": 130,
          "raw_elo_rating": 1452.8690750388523,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "minimal",
          "repair_status": "repaired",
          "score": 18.859141711297916,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 0
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 122,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 47,
          "draws": 111,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "minimal",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "google/gemini-3.6-flash",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 10,
          "model": "google/gemini-3.6-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-4492f6d65cd6280b",
          "rated_matches": 122,
          "raw_elo_rating": 1442.864101000397,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "minimal",
          "repair_status": "first_pass",
          "score": 16.362895246809455,
          "uncertainty": 1.3334817333716131,
          "unilateral_faults": 0,
          "wins": 1
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 88,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 44,
          "draws": 82,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "google/gemini-3.6-flash",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 5,
          "model": "google/gemini-3.6-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-62275b0c39dda32a",
          "rated_matches": 88,
          "raw_elo_rating": 1448.5362643626052,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 16.214567763911244,
          "uncertainty": 9.249894000318006,
          "unilateral_faults": 0,
          "wins": 1
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 130,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 47,
          "draws": 118,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "minimal",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "google/gemini-3.6-flash",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 12,
          "model": "google/gemini-3.6-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-9c8b43dc41bad760",
          "rated_matches": 130,
          "raw_elo_rating": 1448.0725924193703,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "minimal",
          "repair_status": "repaired",
          "score": 17.782763035404734,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 0
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 86,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 43,
          "draws": 72,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-4.1",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "omitted",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 12,
          "model": "gpt-4.1",
          "point_rating_method": "sequential_elo",
          "public_id": "E-e4707b8e4c581ede",
          "rated_matches": 86,
          "raw_elo_rating": 1460.2386314581393,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "omitted",
          "reasoning_setting": "none",
          "repair_status": "repaired",
          "score": 18.7319500025143,
          "uncertainty": 9.855626741889738,
          "unilateral_faults": 0,
          "wins": 2
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 0,
          "capped_draws": 0,
          "coverage_status": "pending",
          "distinct_rated_opponents": 0,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "low",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5",
            "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-21T14:20:15Z",
          "losses": 0,
          "model": "gpt-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-4f8f0a47f75ab6b7",
          "rated_matches": 0,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "low",
          "repair_status": "first_pass",
          "unilateral_faults": 0,
          "wins": 0
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 76,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 37,
          "draws": 58,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 16,
          "model": "gpt-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-5bccb9b671ce5eae",
          "rated_matches": 76,
          "raw_elo_rating": 1471.072947000906,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "first_pass",
          "score": 20.557432544949897,
          "uncertainty": 13.230288229818967,
          "unilateral_faults": 0,
          "wins": 2
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 82,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 36,
          "draws": 51,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "xhigh",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.4",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 9,
          "model": "gpt-5.4",
          "point_rating_method": "sequential_elo",
          "public_id": "E-4aa582caf9d9f6da",
          "rated_matches": 82,
          "raw_elo_rating": 1621.61381435049,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "xhigh",
          "repair_status": "first_pass",
          "score": 54.7169870956697,
          "uncertainty": 11.132129994845172,
          "unilateral_faults": 0,
          "wins": 22
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 77,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 34,
          "draws": 68,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.4",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 4,
          "model": "gpt-5.4",
          "point_rating_method": "sequential_elo",
          "public_id": "E-67423a89b95a1aba",
          "rated_matches": 77,
          "raw_elo_rating": 1493.0766723506626,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 25.561074219037017,
          "uncertainty": 12.86385170722978,
          "unilateral_faults": 0,
          "wins": 5
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 72,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 31,
          "draws": 61,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.4",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 10,
          "model": "gpt-5.4",
          "point_rating_method": "sequential_elo",
          "public_id": "E-89c7c830b0d1a5cf",
          "rated_matches": 72,
          "raw_elo_rating": 1458.3461864208352,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 17.424895818830112,
          "uncertainty": 14.770573598065289,
          "unilateral_faults": 0,
          "wins": 1
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 86,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 42,
          "draws": 81,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.4",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 4,
          "model": "gpt-5.4",
          "point_rating_method": "sequential_elo",
          "public_id": "E-98ddce22d3eb5886",
          "rated_matches": 86,
          "raw_elo_rating": 1461.7295454760624,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 19.06652602077495,
          "uncertainty": 9.855626741889738,
          "unilateral_faults": 0,
          "wins": 1
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 82,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 40,
          "draws": 70,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.4",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 8,
          "model": "gpt-5.4",
          "point_rating_method": "sequential_elo",
          "public_id": "E-f4948a32cdd115a9",
          "rated_matches": 82,
          "raw_elo_rating": 1463.1177660210396,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 19.148888518137927,
          "uncertainty": 11.132129994845172,
          "unilateral_faults": 0,
          "wins": 4
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 86,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 42,
          "draws": 84,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.4-mini",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 2,
          "model": "gpt-5.4-mini",
          "point_rating_method": "sequential_elo",
          "public_id": "E-322cbb8be1559087",
          "rated_matches": 86,
          "raw_elo_rating": 1463.998408715422,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 19.57568162564367,
          "uncertainty": 9.855626741889738,
          "unilateral_faults": 0,
          "wins": 0
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 90,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 43,
          "draws": 84,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.4-mini",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 3,
          "model": "gpt-5.4-mini",
          "point_rating_method": "sequential_elo",
          "public_id": "E-6724998b59176607",
          "rated_matches": 90,
          "raw_elo_rating": 1472.1832965878284,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 21.626339283900553,
          "uncertainty": 8.664241836095918,
          "unilateral_faults": 0,
          "wins": 3
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 88,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 44,
          "draws": 81,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.4-nano",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-09T17:30:50Z",
          "losses": 7,
          "model": "gpt-5.4-nano",
          "point_rating_method": "sequential_elo",
          "public_id": "E-038a95fb13c8aa94",
          "rated_matches": 88,
          "raw_elo_rating": 1459.5120314275132,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "repaired",
          "score": 18.67763967670251,
          "uncertainty": 9.249894000318006,
          "unilateral_faults": 0,
          "wins": 0
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 86,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 43,
          "draws": 75,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.4-nano",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 7,
          "model": "gpt-5.4-nano",
          "point_rating_method": "sequential_elo",
          "public_id": "E-be95cc83ce87847c",
          "rated_matches": 86,
          "raw_elo_rating": 1463.5204302042953,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "repaired",
          "score": 19.4684184668401,
          "uncertainty": 9.855626741889738,
          "unilateral_faults": 0,
          "wins": 4
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 80,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 38,
          "draws": 77,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.4-nano",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 3,
          "model": "gpt-5.4-nano",
          "point_rating_method": "sequential_elo",
          "public_id": "E-d96eaa4f1d20c47b",
          "rated_matches": 80,
          "raw_elo_rating": 1475.7131921870432,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "repaired",
          "score": 21.854529388279282,
          "uncertainty": 11.805555555555554,
          "unilateral_faults": 0,
          "wins": 0
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 86,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 43,
          "draws": 77,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 9,
          "model": "gpt-5.5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-51e935956fa76015",
          "rated_matches": 86,
          "raw_elo_rating": 1475.225904404823,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 22.09524395964808,
          "uncertainty": 9.855626741889738,
          "unilateral_faults": 0,
          "wins": 0
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 74,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 37,
          "draws": 45,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 9,
          "model": "gpt-5.5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-8460841e3919c568",
          "rated_matches": 74,
          "raw_elo_rating": 1576.1121672722809,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 43.99378748372811,
          "uncertainty": 13.985026918962571,
          "unilateral_faults": 0,
          "wins": 20
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 66,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 31,
          "draws": 58,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "xhigh",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.6-luna",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 3,
          "model": "gpt-5.6-luna",
          "point_rating_method": "sequential_elo",
          "public_id": "E-02a02961ddfed4cf",
          "rated_matches": 66,
          "raw_elo_rating": 1500.3602776554874,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "xhigh",
          "repair_status": "first_pass",
          "score": 26.392941660287374,
          "uncertainty": 17.33472217815261,
          "unilateral_faults": 0,
          "wins": 5
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 64,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 31,
          "draws": 58,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.6-luna",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 6,
          "model": "gpt-5.6-luna",
          "point_rating_method": "sequential_elo",
          "public_id": "E-18fbed3cbf75c274",
          "rated_matches": 64,
          "raw_elo_rating": 1446.6966388554522,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 14.182848437029604,
          "uncertainty": 18.26736729460423,
          "unilateral_faults": 0,
          "wins": 0
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 66,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 30,
          "draws": 63,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.6-luna",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 2,
          "model": "gpt-5.6-luna",
          "point_rating_method": "sequential_elo",
          "public_id": "E-2f3ae5ed2aa83217",
          "rated_matches": 66,
          "raw_elo_rating": 1515.1687546699268,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 29.716112021846637,
          "uncertainty": 17.33472217815261,
          "unilateral_faults": 0,
          "wins": 1
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 88,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 44,
          "draws": 75,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "xhigh",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.6-luna",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-10T05:30:29Z",
          "losses": 10,
          "model": "gpt-5.6-luna",
          "point_rating_method": "sequential_elo",
          "public_id": "E-a30e455ba172d80e",
          "rated_matches": 88,
          "raw_elo_rating": 1467.0307143374596,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "xhigh",
          "repair_status": "repaired",
          "score": 20.364907326166584,
          "uncertainty": 9.249894000318006,
          "unilateral_faults": 0,
          "wins": 3
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 86,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 43,
          "draws": 84,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.6-luna",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-10T05:30:29Z",
          "losses": 2,
          "model": "gpt-5.6-luna",
          "point_rating_method": "sequential_elo",
          "public_id": "E-ba4589e1cf2c827b",
          "rated_matches": 86,
          "raw_elo_rating": 1466.444458797462,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 20.124599730294026,
          "uncertainty": 9.855626741889738,
          "unilateral_faults": 0,
          "wins": 0
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 72,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 36,
          "draws": 66,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.6-luna",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-10T05:30:29Z",
          "losses": 6,
          "model": "gpt-5.6-luna",
          "point_rating_method": "sequential_elo",
          "public_id": "E-e2dda893ae4363f2",
          "rated_matches": 72,
          "raw_elo_rating": 1467.7463855821793,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 19.534394534685426,
          "uncertainty": 14.770573598065289,
          "unilateral_faults": 0,
          "wins": 0
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 74,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 37,
          "draws": 59,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.6-sol",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-10T05:30:29Z",
          "losses": 9,
          "model": "gpt-5.6-sol",
          "point_rating_method": "sequential_elo",
          "public_id": "E-0420ca9039edc6fb",
          "rated_matches": 74,
          "raw_elo_rating": 1496.8193553515018,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 26.199687374521076,
          "uncertainty": 13.985026918962571,
          "unilateral_faults": 0,
          "wins": 6
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 78,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 39,
          "draws": 39,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.6-sol",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-10T05:30:29Z",
          "losses": 12,
          "model": "gpt-5.6-sol",
          "point_rating_method": "sequential_elo",
          "public_id": "E-087d760c91df7f17",
          "rated_matches": 78,
          "raw_elo_rating": 1581.8188124317824,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "repaired",
          "score": 45.54023061897745,
          "uncertainty": 12.5043950463012,
          "unilateral_faults": 0,
          "wins": 27
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 68,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 30,
          "draws": 40,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.6-sol",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 1,
          "model": "gpt-5.6-sol",
          "point_rating_method": "sequential_elo",
          "public_id": "E-1d0646e1538c1b7a",
          "rated_matches": 68,
          "raw_elo_rating": 1623.7312204453247,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 54.238717509734094,
          "uncertainty": 16.4429265428846,
          "unilateral_faults": 0,
          "wins": 27
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 90,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 37,
          "draws": 15,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "xhigh",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.6-sol",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-10T05:30:29Z",
          "losses": 11,
          "model": "gpt-5.6-sol",
          "point_rating_method": "sequential_elo",
          "public_id": "E-33dc9365cfacf9c0",
          "rated_matches": 90,
          "raw_elo_rating": 1817.1768615381052,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "xhigh",
          "repair_status": "first_pass",
          "score": 99.04634600393882,
          "uncertainty": 8.664241836095918,
          "unilateral_faults": 0,
          "wins": 64
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 70,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 30,
          "draws": 59,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.6-sol",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 5,
          "model": "gpt-5.6-sol",
          "point_rating_method": "sequential_elo",
          "public_id": "E-7b3b7d80a8f97b36",
          "rated_matches": 70,
          "raw_elo_rating": 1500.5055646014496,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 26.738936634036737,
          "uncertainty": 15.58908290969266,
          "unilateral_faults": 0,
          "wins": 6
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 68,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 31,
          "draws": 13,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "xhigh",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.6-sol",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 0,
          "model": "gpt-5.6-sol",
          "point_rating_method": "sequential_elo",
          "public_id": "E-f939ae7c9b81e0cc",
          "rated_matches": 68,
          "raw_elo_rating": 1827.6494148740956,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "xhigh",
          "repair_status": "repaired",
          "score": 100.0,
          "uncertainty": 16.4429265428846,
          "unilateral_faults": 0,
          "wins": 55
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 90,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 37,
          "draws": 52,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "xhigh",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.6-terra",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-10T05:30:29Z",
          "losses": 20,
          "model": "gpt-5.6-terra",
          "point_rating_method": "sequential_elo",
          "public_id": "E-1b12482867c807c9",
          "rated_matches": 90,
          "raw_elo_rating": 1584.5440638410278,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "xhigh",
          "repair_status": "first_pass",
          "score": 46.84121932685183,
          "uncertainty": 8.664241836095918,
          "unilateral_faults": 0,
          "wins": 18
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 86,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 42,
          "draws": 76,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.6-terra",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-10T05:30:29Z",
          "losses": 9,
          "model": "gpt-5.6-terra",
          "point_rating_method": "sequential_elo",
          "public_id": "E-82ad98d8d570daab",
          "rated_matches": 86,
          "raw_elo_rating": 1492.4957620772557,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "repaired",
          "score": 25.970772760443374,
          "uncertainty": 9.855626741889738,
          "unilateral_faults": 0,
          "wins": 1
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 104,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 52,
          "draws": 91,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.6-terra",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-10T05:30:29Z",
          "losses": 9,
          "model": "gpt-5.6-terra",
          "point_rating_method": "sequential_elo",
          "public_id": "E-c6593bd789768bdb",
          "rated_matches": 104,
          "raw_elo_rating": 1499.4681276807262,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "repaired",
          "score": 28.399082893812732,
          "uncertainty": 5.045003647426665,
          "unilateral_faults": 0,
          "wins": 4
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 22,
          "capped_draws": 0,
          "coverage_status": "under_covered",
          "distinct_rated_opponents": 11,
          "draws": 18,
          "evaluated_setting_identity": {
            "canonical_provider_route": "unknown_legacy",
            "effective_request_value": "enabled",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "inclusionai/ling-3.0-flash:free",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 4,
          "model": "inclusionai/ling-3.0-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-129026c5e53b35ad",
          "rated_matches": 22,
          "raw_elo_rating": 1438.7847701679702,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "enabled",
          "repair_status": "repaired",
          "score": 4.824111939258095,
          "uncertainty": 60.5072070285374,
          "unilateral_faults": 0,
          "wins": 0
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 118,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 47,
          "draws": 110,
          "evaluated_setting_identity": {
            "canonical_provider_route": "unknown_legacy",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "inclusionai/ling-3.0-flash:free",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 7,
          "model": "inclusionai/ling-3.0-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-fc495094a55d2f94",
          "rated_matches": 118,
          "raw_elo_rating": 1445.7308308182332,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 16.871313010451086,
          "uncertainty": 2.084924851410568,
          "unilateral_faults": 0,
          "wins": 1
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 106,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 41,
          "draws": 101,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "enabled",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "meituan/longcat-2.0",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 3,
          "model": "meituan/longcat-2.0",
          "point_rating_method": "sequential_elo",
          "public_id": "E-a00d8e3eb7dd07cf",
          "rated_matches": 106,
          "raw_elo_rating": 1476.8316916886058,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "enabled",
          "repair_status": "repaired",
          "score": 23.401496235109175,
          "uncertainty": 4.586824452283178,
          "unilateral_faults": 0,
          "wins": 2
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 100,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 50,
          "draws": 94,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "meituan/longcat-2.0",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 5,
          "model": "meituan/longcat-2.0",
          "point_rating_method": "sequential_elo",
          "public_id": "E-a0c74818516a7f27",
          "rated_matches": 100,
          "raw_elo_rating": 1457.7390320719044,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "none",
          "repair_status": "repaired",
          "score": 18.862874029135362,
          "uncertainty": 6.001859510499461,
          "unilateral_faults": 0,
          "wins": 1
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 68,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 31,
          "draws": 57,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "minimal",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "meta/muse-spark-1.2",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-08-13T16:58:34Z",
          "losses": 8,
          "model": "meta/muse-spark-1.2",
          "point_rating_method": "sequential_elo",
          "public_id": "E-0a492b508106c7e8",
          "rated_matches": 68,
          "raw_elo_rating": 1455.6017691862596,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "minimal",
          "repair_status": "first_pass",
          "score": 16.50878695816217,
          "uncertainty": 16.4429265428846,
          "unilateral_faults": 0,
          "wins": 3
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 67,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 31,
          "draws": 50,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "meta/muse-spark-1.2",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-08-13T16:58:34Z",
          "losses": 6,
          "model": "meta/muse-spark-1.2",
          "point_rating_method": "sequential_elo",
          "public_id": "E-2b12f5618349c056",
          "rated_matches": 67,
          "raw_elo_rating": 1509.5573026507243,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 28.53778014221482,
          "uncertainty": 16.883906259083243,
          "unilateral_faults": 0,
          "wins": 11
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 72,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 35,
          "draws": 69,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "minimax/minimax-m3",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 3,
          "model": "minimax/minimax-m3",
          "point_rating_method": "sequential_elo",
          "public_id": "E-1e46941293882535",
          "rated_matches": 72,
          "raw_elo_rating": 1455.210402384003,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 16.721194515766282,
          "uncertainty": 14.770573598065289,
          "unilateral_faults": 0,
          "wins": 0
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 86,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 39,
          "draws": 71,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "enabled",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "minimax/minimax-m3",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 14,
          "model": "minimax/minimax-m3",
          "point_rating_method": "sequential_elo",
          "public_id": "E-cad87bcb23d33fef",
          "rated_matches": 86,
          "raw_elo_rating": 1429.2739821056432,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "enabled",
          "repair_status": "repaired",
          "score": 11.783172968660383,
          "uncertainty": 9.855626741889738,
          "unilateral_faults": 0,
          "wins": 1
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 118,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 56,
          "draws": 91,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "enabled",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "moonshotai/kimi-k2.7-code",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 23,
          "model": "moonshotai/kimi-k2.7-code",
          "point_rating_method": "sequential_elo",
          "public_id": "E-85c8a9372a607001",
          "rated_matches": 118,
          "raw_elo_rating": 1474.596618403244,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "enabled",
          "repair_status": "repaired",
          "score": 23.349084470138546,
          "uncertainty": 2.084924851410568,
          "unilateral_faults": 0,
          "wins": 4
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 104,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 39,
          "draws": 79,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "moonshotai/kimi-k3",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T14:00:00Z",
          "losses": 18,
          "model": "moonshotai/kimi-k3",
          "point_rating_method": "sequential_elo",
          "public_id": "E-0c4144684fc36307",
          "rated_matches": 104,
          "raw_elo_rating": 1460.9653251764248,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "first_pass",
          "score": 19.758668893473487,
          "uncertainty": 5.045003647426665,
          "unilateral_faults": 0,
          "wins": 7
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 130,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 49,
          "draws": 112,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "max",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "moonshotai/kimi-k3",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T14:00:00Z",
          "losses": 12,
          "model": "moonshotai/kimi-k3",
          "point_rating_method": "sequential_elo",
          "public_id": "E-1beeecccf3f2c84f",
          "rated_matches": 130,
          "raw_elo_rating": 1474.3344994862955,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "max",
          "repair_status": "repaired",
          "score": 23.676197661918458,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 6
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 154,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 57,
          "draws": 136,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "low",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "moonshotai/kimi-k3",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T14:00:00Z",
          "losses": 10,
          "model": "moonshotai/kimi-k3",
          "point_rating_method": "sequential_elo",
          "public_id": "E-d3d3da42e99695b1",
          "rated_matches": 154,
          "raw_elo_rating": 1468.0575574041725,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "low",
          "repair_status": "first_pass",
          "score": 22.900288191407675,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 8
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 84,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 41,
          "draws": 71,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "nex-agi/nex-n2-pro",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-11T17:22:09Z",
          "losses": 11,
          "model": "nex-agi/nex-n2-pro",
          "point_rating_method": "sequential_elo",
          "public_id": "E-811f47e902ce0d21",
          "rated_matches": 84,
          "raw_elo_rating": 1451.0500885064464,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "none",
          "repair_status": "repaired",
          "score": 16.55738720588751,
          "uncertainty": 10.482614454664043,
          "unilateral_faults": 0,
          "wins": 2
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 70,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 34,
          "draws": 62,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "nvidia/nemotron-3-ultra-550b-a55b",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 7,
          "model": "nvidia/nemotron-3-ultra-550b-a55b",
          "point_rating_method": "sequential_elo",
          "public_id": "E-2404d10bab26a254",
          "rated_matches": 70,
          "raw_elo_rating": 1474.5426351145522,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "repaired",
          "score": 20.912595566958643,
          "uncertainty": 15.58908290969266,
          "unilateral_faults": 0,
          "wins": 1
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 68,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 34,
          "draws": 56,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "nvidia/nemotron-3-ultra-550b-a55b",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-11T17:22:09Z",
          "losses": 11,
          "model": "nvidia/nemotron-3-ultra-550b-a55b",
          "point_rating_method": "sequential_elo",
          "public_id": "E-abd2cae3e3ff9bdb",
          "rated_matches": 68,
          "raw_elo_rating": 1460.7049054242543,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "repaired",
          "score": 17.653981773305354,
          "uncertainty": 16.4429265428846,
          "unilateral_faults": 0,
          "wins": 1
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 90,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 44,
          "draws": 84,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "nvidia/nemotron-3-ultra-550b-a55b",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 5,
          "model": "nvidia/nemotron-3-ultra-550b-a55b",
          "point_rating_method": "sequential_elo",
          "public_id": "E-bd70ebbd81fdbef0",
          "rated_matches": 90,
          "raw_elo_rating": 1453.1606606288503,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "repaired",
          "score": 17.357469503708607,
          "uncertainty": 8.664241836095918,
          "unilateral_faults": 0,
          "wins": 1
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 86,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 42,
          "draws": 77,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "openai/gpt-oss-120b",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 5,
          "model": "openai/gpt-oss-120b",
          "point_rating_method": "sequential_elo",
          "public_id": "E-8f0c6569aa132f8e",
          "rated_matches": 86,
          "raw_elo_rating": 1473.9362990217546,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 21.805843612607568,
          "uncertainty": 9.855626741889738,
          "unilateral_faults": 0,
          "wins": 4
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 74,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 37,
          "draws": 59,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "openai/gpt-oss-120b",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 15,
          "model": "openai/gpt-oss-120b",
          "point_rating_method": "sequential_elo",
          "public_id": "E-e5b4a3586049e1c9",
          "rated_matches": 74,
          "raw_elo_rating": 1442.0685143240635,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "repaired",
          "score": 13.91305101107773,
          "uncertainty": 13.985026918962571,
          "unilateral_faults": 0,
          "wins": 0
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 118,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 41,
          "draws": 112,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "enabled",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "poolside/laguna-s-2.1",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 4,
          "model": "poolside/laguna-s-2.1",
          "point_rating_method": "sequential_elo",
          "public_id": "E-7164ee63b9dd911a",
          "rated_matches": 116,
          "raw_elo_rating": 1468.6265515338287,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "enabled",
          "repair_status": "first_pass",
          "score": 21.9393094022954,
          "uncertainty": 2.4750163521024238,
          "unilateral_faults": 0,
          "wins": 0
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 118,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 44,
          "draws": 113,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "enabled",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "poolside/laguna-s-2.1",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 5,
          "model": "poolside/laguna-s-2.1",
          "point_rating_method": "sequential_elo",
          "public_id": "E-ba56689188a301b2",
          "rated_matches": 118,
          "raw_elo_rating": 1461.650267468705,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "enabled",
          "repair_status": "repaired",
          "score": 20.443793826539274,
          "uncertainty": 2.084924851410568,
          "unilateral_faults": 0,
          "wins": 0
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 106,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 52,
          "draws": 99,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "poolside/laguna-s-2.1",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 4,
          "model": "poolside/laguna-s-2.1",
          "point_rating_method": "sequential_elo",
          "public_id": "E-d8c7a78cc7f666dc",
          "rated_matches": 106,
          "raw_elo_rating": 1457.0890590046167,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "none",
          "repair_status": "repaired",
          "score": 18.971051988167996,
          "uncertainty": 4.586824452283178,
          "unilateral_faults": 0,
          "wins": 3
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 80,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 40,
          "draws": 66,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "qwen/qwen3.7-max",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 6,
          "model": "qwen/qwen3.7-max",
          "point_rating_method": "sequential_elo",
          "public_id": "E-5f64c2ae9860ba38",
          "rated_matches": 80,
          "raw_elo_rating": 1485.2151308299296,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 23.986859461426256,
          "uncertainty": 11.805555555555554,
          "unilateral_faults": 0,
          "wins": 8
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 100,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 48,
          "draws": 83,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "enabled",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "qwen/qwen3.7-max",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 13,
          "model": "qwen/qwen3.7-max",
          "point_rating_method": "sequential_elo",
          "public_id": "E-95265340f8562bfd",
          "rated_matches": 100,
          "raw_elo_rating": 1462.125463708624,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "enabled",
          "repair_status": "repaired",
          "score": 19.847233163024622,
          "uncertainty": 6.001859510499461,
          "unilateral_faults": 0,
          "wins": 4
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 92,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 45,
          "draws": 91,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "qwen/qwen3.7-plus",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 1,
          "model": "qwen/qwen3.7-plus",
          "point_rating_method": "sequential_elo",
          "public_id": "E-010dafcd7561851a",
          "rated_matches": 92,
          "raw_elo_rating": 1453.658322014426,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "none",
          "repair_status": "repaired",
          "score": 17.570880513249598,
          "uncertainty": 8.09758473652126,
          "unilateral_faults": 0,
          "wins": 0
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 86,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 39,
          "draws": 81,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "enabled",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "qwen/qwen3.7-plus",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 4,
          "model": "qwen/qwen3.7-plus",
          "point_rating_method": "sequential_elo",
          "public_id": "E-57293d5b71f14882",
          "rated_matches": 86,
          "raw_elo_rating": 1480.3725891120614,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "enabled",
          "repair_status": "repaired",
          "score": 23.250211486876427,
          "uncertainty": 9.855626741889738,
          "unilateral_faults": 0,
          "wins": 1
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 17,
          "capped_draws": 0,
          "coverage_status": "under_covered",
          "distinct_rated_opponents": 8,
          "draws": 14,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "minimal",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "qwen/qwen3.8-max",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 3,
          "model": "qwen/qwen3.8-max",
          "point_rating_method": "sequential_elo",
          "public_id": "E-20f9463bfdcb2c8a",
          "rated_matches": 17,
          "raw_elo_rating": 1461.545523222252,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "minimal",
          "repair_status": "first_pass",
          "score": 7.491362721335916,
          "uncertainty": 74.10113019775793,
          "unilateral_faults": 0,
          "wins": 0
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 17,
          "capped_draws": 0,
          "coverage_status": "under_covered",
          "distinct_rated_opponents": 9,
          "draws": 13,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "xhigh",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "qwen/qwen3.8-max",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-08-18T19:04:19Z",
          "losses": 1,
          "model": "qwen/qwen3.8-max",
          "point_rating_method": "sequential_elo",
          "public_id": "E-51f44e67337145d4",
          "rated_matches": 17,
          "raw_elo_rating": 1519.2581453563312,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "xhigh",
          "repair_status": "first_pass",
          "score": 20.442652389870492,
          "uncertainty": 74.10113019775793,
          "unilateral_faults": 0,
          "wins": 3
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 20,
          "capped_draws": 0,
          "coverage_status": "under_covered",
          "distinct_rated_opponents": 10,
          "draws": 18,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "qwen/qwen3.8-max",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 2,
          "model": "qwen/qwen3.8-max",
          "point_rating_method": "sequential_elo",
          "public_id": "E-7ca9241c6a1cf54f",
          "rated_matches": 20,
          "raw_elo_rating": 1473.6963543985923,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 11.78759779354171,
          "uncertainty": 65.3589451179962,
          "unilateral_faults": 0,
          "wins": 0
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 14,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 7,
          "draws": 9,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "low",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "stealth/ox-alpha",
            "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-08-22T00:27:26Z",
          "losses": 5,
          "model": "stealth/ox-alpha",
          "point_rating_method": "sequential_elo",
          "public_id": "E-06f983f13f9519d4",
          "rated_matches": 14,
          "raw_elo_rating": 1441.0405304647181,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "low",
          "repair_status": "first_pass",
          "score": 0.8704497902647038,
          "uncertainty": 85.34944487358055,
          "unilateral_faults": 0,
          "wins": 0
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 14,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 7,
          "draws": 8,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "stealth/ox-alpha",
            "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-08-22T00:27:26Z",
          "losses": 2,
          "model": "stealth/ox-alpha",
          "point_rating_method": "sequential_elo",
          "public_id": "E-427d180a6aa40aa2",
          "rated_matches": 14,
          "raw_elo_rating": 1521.106547069262,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "first_pass",
          "score": 18.838064764369765,
          "uncertainty": 85.34944487358055,
          "unilateral_faults": 0,
          "wins": 4
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 14,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 7,
          "draws": 6,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "max",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "stealth/ox-alpha",
            "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-08-22T00:27:26Z",
          "losses": 1,
          "model": "stealth/ox-alpha",
          "point_rating_method": "sequential_elo",
          "public_id": "E-844b5265eeccbffb",
          "rated_matches": 14,
          "raw_elo_rating": 1575.5462752401954,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "max",
          "repair_status": "first_pass",
          "score": 31.0548842909548,
          "uncertainty": 85.34944487358055,
          "unilateral_faults": 0,
          "wins": 7
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 14,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 7,
          "draws": 9,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "stealth/ox-alpha",
            "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-08-22T00:27:26Z",
          "losses": 3,
          "model": "stealth/ox-alpha",
          "point_rating_method": "sequential_elo",
          "public_id": "E-8ad03916301062ed",
          "rated_matches": 14,
          "raw_elo_rating": 1488.2202220411896,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "first_pass",
          "score": 11.458044487650438,
          "uncertainty": 85.34944487358055,
          "unilateral_faults": 0,
          "wins": 2
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 14,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 7,
          "draws": 10,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "low",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "stealth/ox-alpha",
            "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-08-22T00:27:26Z",
          "losses": 4,
          "model": "stealth/ox-alpha",
          "point_rating_method": "sequential_elo",
          "public_id": "E-aac195c51848d687",
          "rated_matches": 14,
          "raw_elo_rating": 1458.6853240806147,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "low",
          "repair_status": "first_pass",
          "score": 4.830117967012544,
          "uncertainty": 85.34944487358055,
          "unilateral_faults": 0,
          "wins": 0
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 14,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 7,
          "draws": 7,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "stealth/ox-alpha",
            "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-08-22T00:27:26Z",
          "losses": 6,
          "model": "stealth/ox-alpha",
          "point_rating_method": "sequential_elo",
          "public_id": "E-b4db3ddedfd59608",
          "rated_matches": 14,
          "raw_elo_rating": 1437.161693598434,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "first_pass",
          "score": 0.0,
          "uncertainty": 85.34944487358055,
          "unilateral_faults": 0,
          "wins": 1
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 14,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 7,
          "draws": 9,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "low",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "stealth/ox-alpha",
            "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-08-22T00:27:26Z",
          "losses": 4,
          "model": "stealth/ox-alpha",
          "point_rating_method": "sequential_elo",
          "public_id": "E-b633c9cf2d63b092",
          "rated_matches": 14,
          "raw_elo_rating": 1463.5225876446907,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "low",
          "repair_status": "first_pass",
          "score": 5.915648294777751,
          "uncertainty": 85.34944487358055,
          "unilateral_faults": 0,
          "wins": 1
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 14,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 7,
          "draws": 4,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "max",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "stealth/ox-alpha",
            "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-08-22T00:27:26Z",
          "losses": 0,
          "model": "stealth/ox-alpha",
          "point_rating_method": "sequential_elo",
          "public_id": "E-f1feaabe79bde601",
          "rated_matches": 14,
          "raw_elo_rating": 1614.7168198608954,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "max",
          "repair_status": "first_pass",
          "score": 39.84514630120195,
          "uncertainty": 85.34944487358055,
          "unilateral_faults": 0,
          "wins": 10
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 86,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 41,
          "draws": 76,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "stepfun/step-3.7-flash",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 9,
          "model": "stepfun/step-3.7-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-0ccea44addccfff0",
          "rated_matches": 86,
          "raw_elo_rating": 1478.1857236712685,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "repaired",
          "score": 22.759457008176497,
          "uncertainty": 9.855626741889738,
          "unilateral_faults": 0,
          "wins": 1
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 72,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 36,
          "draws": 66,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "tencent/hy3-preview",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 6,
          "model": "tencent/hy3-preview",
          "point_rating_method": "sequential_elo",
          "public_id": "E-d910e47dd13c2c71",
          "rated_matches": 72,
          "raw_elo_rating": 1444.8163020312015,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "repaired",
          "score": 14.388654431203785,
          "uncertainty": 14.770573598065289,
          "unilateral_faults": 0,
          "wins": 0
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 68,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 32,
          "draws": 53,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "tencent/hy3-preview",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 12,
          "model": "tencent/hy3-preview",
          "point_rating_method": "sequential_elo",
          "public_id": "E-fbf6af15f65f01d7",
          "rated_matches": 66,
          "raw_elo_rating": 1444.0591535680944,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "repaired",
          "score": 13.758406271721789,
          "uncertainty": 17.33472217815261,
          "unilateral_faults": 2,
          "wins": 1
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 102,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 50,
          "draws": 90,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "thinkingmachines/inkling",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 10,
          "model": "thinkingmachines/inkling",
          "point_rating_method": "sequential_elo",
          "public_id": "E-66a4f0abd099d8f1",
          "rated_matches": 102,
          "raw_elo_rating": 1484.3681592549508,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "repaired",
          "score": 24.925858625367727,
          "uncertainty": 5.516463908214657,
          "unilateral_faults": 0,
          "wins": 2
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 124,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 43,
          "draws": 111,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "max",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "thinkingmachines/inkling",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 9,
          "model": "thinkingmachines/inkling",
          "point_rating_method": "sequential_elo",
          "public_id": "E-9468e854340a4e9b",
          "rated_matches": 122,
          "raw_elo_rating": 1459.031259226249,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "max",
          "repair_status": "repaired",
          "score": 19.990967262210003,
          "uncertainty": 1.3334817333716131,
          "unilateral_faults": 0,
          "wins": 2
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 18,
          "capped_draws": 0,
          "coverage_status": "under_covered",
          "distinct_rated_opponents": 9,
          "draws": 18,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "thinkingmachines/inkling-small",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 0,
          "model": "thinkingmachines/inkling-small",
          "point_rating_method": "sequential_elo",
          "public_id": "E-161b7f406eb4d549",
          "rated_matches": 18,
          "raw_elo_rating": 1492.6020204364095,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 15.025055106927441,
          "uncertainty": 70.95786693528086,
          "unilateral_faults": 0,
          "wins": 0
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 20,
          "capped_draws": 0,
          "coverage_status": "under_covered",
          "distinct_rated_opponents": 11,
          "draws": 20,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "thinkingmachines/inkling-small",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 0,
          "model": "thinkingmachines/inkling-small",
          "point_rating_method": "sequential_elo",
          "public_id": "E-647caf2136958821",
          "rated_matches": 20,
          "raw_elo_rating": 1484.2472717904682,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "repaired",
          "score": 14.155329190210882,
          "uncertainty": 65.3589451179962,
          "unilateral_faults": 0,
          "wins": 0
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 16,
          "capped_draws": 0,
          "coverage_status": "under_covered",
          "distinct_rated_opponents": 9,
          "draws": 15,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "max",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "thinkingmachines/inkling-small",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 1,
          "model": "thinkingmachines/inkling-small",
          "point_rating_method": "sequential_elo",
          "public_id": "E-d92a785d012f8e1b",
          "rated_matches": 16,
          "raw_elo_rating": 1482.473546162997,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "max",
          "repair_status": "first_pass",
          "score": 11.574430248545012,
          "uncertainty": 77.5178125181665,
          "unilateral_faults": 0,
          "wins": 0
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 144,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 53,
          "draws": 72,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "x-ai/grok-4.5",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T14:00:00Z",
          "losses": 24,
          "model": "x-ai/grok-4.5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-0576181f89efa7a7",
          "rated_matches": 144,
          "raw_elo_rating": 1594.752196706652,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "repaired",
          "score": 51.08735602238606,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 48
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 127,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 50,
          "draws": 113,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "low",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "x-ai/grok-4.5",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T14:00:00Z",
          "losses": 9,
          "model": "x-ai/grok-4.5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-88ab68f664bd3ea0",
          "rated_matches": 127,
          "raw_elo_rating": 1491.590095915884,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "low",
          "repair_status": "first_pass",
          "score": 27.457151552126646,
          "uncertainty": 0.444173824159213,
          "unilateral_faults": 0,
          "wins": 5
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 98,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 49,
          "draws": 69,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "x-ai/grok-4.5",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T14:00:00Z",
          "losses": 16,
          "model": "x-ai/grok-4.5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-da5ea0258e71b6ab",
          "rated_matches": 98,
          "raw_elo_rating": 1492.6220047983245,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 26.601192408895606,
          "uncertainty": 6.501890762960602,
          "unilateral_faults": 0,
          "wins": 13
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 92,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 44,
          "draws": 86,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "enabled",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "x-ai/grok-build-0.1",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 3,
          "model": "x-ai/grok-build-0.1",
          "point_rating_method": "sequential_elo",
          "public_id": "E-99592fa0331c6679",
          "rated_matches": 92,
          "raw_elo_rating": 1471.922484272434,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "enabled",
          "repair_status": "repaired",
          "score": 21.669541208427077,
          "uncertainty": 8.09758473652126,
          "unilateral_faults": 0,
          "wins": 3
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 66,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 33,
          "draws": 65,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "xiaomi/mimo-v2.5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-01T00:15:48Z",
          "losses": 1,
          "model": "xiaomi/mimo-v2.5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-39b08fe4c0318552",
          "rated_matches": 66,
          "raw_elo_rating": 1469.8584606204145,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 19.548028827872443,
          "uncertainty": 17.33472217815261,
          "unilateral_faults": 0,
          "wins": 0
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 90,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 41,
          "draws": 75,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "enabled",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "xiaomi/mimo-v2.5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 11,
          "model": "xiaomi/mimo-v2.5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-5b213ae773e821cc",
          "rated_matches": 90,
          "raw_elo_rating": 1489.18525311898,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "enabled",
          "repair_status": "repaired",
          "score": 25.441748388952313,
          "uncertainty": 8.664241836095918,
          "unilateral_faults": 0,
          "wins": 4
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 74,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 37,
          "draws": 60,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "xiaomi/mimo-v2.5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T06:10:40Z",
          "losses": 11,
          "model": "xiaomi/mimo-v2.5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-9077f1e8e006290b",
          "rated_matches": 74,
          "raw_elo_rating": 1502.3343523013145,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "repaired",
          "score": 27.437307852969795,
          "uncertainty": 13.985026918962571,
          "unilateral_faults": 0,
          "wins": 3
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 80,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 37,
          "draws": 76,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "xiaomi/mimo-v2.5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-01T00:15:48Z",
          "losses": 4,
          "model": "xiaomi/mimo-v2.5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-a5f372b0e5962ee5",
          "rated_matches": 80,
          "raw_elo_rating": 1460.0313175143754,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "repaired",
          "score": 18.335359856187495,
          "uncertainty": 11.805555555555554,
          "unilateral_faults": 0,
          "wins": 0
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 88,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 41,
          "draws": 77,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "xiaomi/mimo-v2.5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T06:10:40Z",
          "losses": 6,
          "model": "xiaomi/mimo-v2.5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-c37f25e181320efb",
          "rated_matches": 88,
          "raw_elo_rating": 1479.0790665127915,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "repaired",
          "score": 23.06867806610496,
          "uncertainty": 9.249894000318006,
          "unilateral_faults": 0,
          "wins": 5
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 78,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 39,
          "draws": 66,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "xiaomi/mimo-v2.5-pro",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 7,
          "model": "xiaomi/mimo-v2.5-pro",
          "point_rating_method": "sequential_elo",
          "public_id": "E-b9f44937a1269e8d",
          "rated_matches": 78,
          "raw_elo_rating": 1491.2790874838233,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 25.222210730949445,
          "uncertainty": 12.5043950463012,
          "unilateral_faults": 0,
          "wins": 5
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 64,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 32,
          "draws": 63,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "z-ai/glm-5.2",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-11T17:22:09Z",
          "losses": 1,
          "model": "z-ai/glm-5.2",
          "point_rating_method": "sequential_elo",
          "public_id": "E-32435b01ac08ed41",
          "rated_matches": 64,
          "raw_elo_rating": 1468.1999436475344,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "repaired",
          "score": 19.008405115879473,
          "uncertainty": 18.26736729460423,
          "unilateral_faults": 0,
          "wins": 0
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 66,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 33,
          "draws": 60,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "z-ai/glm-5.2",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 6,
          "model": "z-ai/glm-5.2",
          "point_rating_method": "sequential_elo",
          "public_id": "E-4959351a96fd2b82",
          "rated_matches": 66,
          "raw_elo_rating": 1435.4886349173833,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "repaired",
          "score": 11.835096161204495,
          "uncertainty": 17.33472217815261,
          "unilateral_faults": 0,
          "wins": 0
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 62,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 31,
          "draws": 58,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "z-ai/glm-5.2",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-11T14:00:45Z",
          "losses": 3,
          "model": "z-ai/glm-5.2",
          "point_rating_method": "sequential_elo",
          "public_id": "E-925b589068dc7268",
          "rated_matches": 62,
          "raw_elo_rating": 1474.219113041954,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "repaired",
          "score": 20.183819862570907,
          "uncertainty": 19.244078834871203,
          "unilateral_faults": 0,
          "wins": 1
        }
      ],
      "GB2-03": [
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 68,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 29,
          "draws": 32,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "xhigh",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-fable-5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-03T17:50:00Z",
          "losses": 7,
          "model": "claude-fable-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-04fa5b762ca703f0",
          "rated_matches": 68,
          "raw_elo_rating": 1699.478327839778,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "xhigh",
          "repair_status": "first_pass",
          "score": 72.45110481946428,
          "uncertainty": 16.4429265428846,
          "unilateral_faults": 0,
          "wins": 29
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 90,
          "capped_draws": 15,
          "coverage_status": "rated",
          "distinct_rated_opponents": 45,
          "draws": 62,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-opus-4-5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "omitted",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 15,
          "model": "claude-opus-4-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-1975db22db58e9b0",
          "rated_matches": 90,
          "raw_elo_rating": 1517.64293491248,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "omitted",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 48.527410514780094,
          "uncertainty": 8.664241836095918,
          "unilateral_faults": 0,
          "wins": 13
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 0,
          "capped_draws": 0,
          "coverage_status": "pending",
          "distinct_rated_opponents": 0,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "legacy_shared_thinking_budget",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-opus-4-5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "budget",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 0,
          "model": "claude-opus-4-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-cef4890e88806969",
          "rated_matches": 0,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "budget",
          "reasoning_setting": "legacy_shared_thinking_budget",
          "repair_status": "first_pass",
          "unilateral_faults": 0,
          "wins": 0
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 152,
          "capped_draws": 9,
          "coverage_status": "rated",
          "distinct_rated_opponents": 62,
          "draws": 41,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-opus-4-5",
            "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 64,
          "model": "claude-opus-4-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-d5810442d7094396",
          "rated_matches": 152,
          "raw_elo_rating": 1439.6013043122741,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "first_pass",
          "score": 39.20269156862466,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 47
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 160,
          "capped_draws": 19,
          "coverage_status": "rated",
          "distinct_rated_opponents": 58,
          "draws": 77,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-opus-4-5",
            "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 48,
          "model": "claude-opus-4-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-dfb18dba94eee30b",
          "rated_matches": 160,
          "raw_elo_rating": 1498.8789320043286,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 47.38893238646811,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 35
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 64,
          "capped_draws": 7,
          "coverage_status": "rated",
          "distinct_rated_opponents": 32,
          "draws": 38,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-opus-4-8",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 15,
          "model": "claude-opus-4-8",
          "point_rating_method": "sequential_elo",
          "public_id": "E-823b961281482cd1",
          "rated_matches": 64,
          "raw_elo_rating": 1445.7477631553459,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 37.68653930194108,
          "uncertainty": 18.26736729460423,
          "unilateral_faults": 0,
          "wins": 11
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 58,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 25,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "xhigh",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-opus-5",
            "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-25T15:48:00Z",
          "losses": 4,
          "model": "claude-opus-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-38759212c025e8eb",
          "rated_matches": 58,
          "raw_elo_rating": 1905.622869125327,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "xhigh",
          "repair_status": "first_pass",
          "score": 100.0,
          "uncertainty": 21.344455490411935,
          "unilateral_faults": 0,
          "wins": 54
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 86,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 43,
          "draws": 11,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-opus-5",
            "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-25T15:48:00Z",
          "losses": 32,
          "model": "claude-opus-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-49aaba66f6b19080",
          "rated_matches": 86,
          "raw_elo_rating": 1627.3893994335508,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 63.34833623672766,
          "uncertainty": 9.855626741889738,
          "unilateral_faults": 0,
          "wins": 43
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 58,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 25,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "xhigh",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-opus-5",
            "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-25T15:48:00Z",
          "losses": 5,
          "model": "claude-opus-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-7caa6c5081d57676",
          "rated_matches": 58,
          "raw_elo_rating": 1886.8165664948144,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "xhigh",
          "repair_status": "first_pass",
          "score": 97.43801622533607,
          "uncertainty": 21.344455490411935,
          "unilateral_faults": 0,
          "wins": 53
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 80,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 40,
          "draws": 4,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-opus-5",
            "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-25T15:48:00Z",
          "losses": 10,
          "model": "claude-opus-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-bd02f4c2907d0a7c",
          "rated_matches": 80,
          "raw_elo_rating": 1847.6520197765583,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 93.14221553912532,
          "uncertainty": 11.805555555555554,
          "unilateral_faults": 0,
          "wins": 66
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 82,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 41,
          "draws": 4,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-opus-5",
            "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-25T15:48:00Z",
          "losses": 5,
          "model": "claude-opus-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-d8babc5495b1a188",
          "rated_matches": 82,
          "raw_elo_rating": 1888.0062822581406,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 98.71307186653274,
          "uncertainty": 11.132129994845172,
          "unilateral_faults": 0,
          "wins": 73
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 90,
          "capped_draws": 1,
          "coverage_status": "rated",
          "distinct_rated_opponents": 45,
          "draws": 24,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-opus-5",
            "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-25T15:48:00Z",
          "losses": 24,
          "model": "claude-opus-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-ecf847457e616425",
          "rated_matches": 90,
          "raw_elo_rating": 1495.7274710121853,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 45.54186550734778,
          "uncertainty": 8.664241836095918,
          "unilateral_faults": 0,
          "wins": 42
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 88,
          "capped_draws": 5,
          "coverage_status": "rated",
          "distinct_rated_opponents": 42,
          "draws": 31,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-sonnet-5",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 17,
          "model": "claude-sonnet-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-0d68a6f35cd9e672",
          "rated_matches": 88,
          "raw_elo_rating": 1613.9042805271881,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 61.57727285827689,
          "uncertainty": 9.249894000318006,
          "unilateral_faults": 0,
          "wins": 40
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 80,
          "capped_draws": 2,
          "coverage_status": "rated",
          "distinct_rated_opponents": 36,
          "draws": 37,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "xhigh",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-sonnet-5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_7fad32_to_brackets_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-19T15:25:00Z",
          "losses": 16,
          "model": "claude-sonnet-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-1c251b669239429c",
          "rated_matches": 80,
          "raw_elo_rating": 1606.464063932883,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_7fad32_to_brackets_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "xhigh",
          "repair_status": "first_pass",
          "score": 60.285165343979514,
          "uncertainty": 11.805555555555554,
          "unilateral_faults": 0,
          "wins": 27
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 60,
          "capped_draws": 2,
          "coverage_status": "rated",
          "distinct_rated_opponents": 29,
          "draws": 19,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "xhigh",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-sonnet-5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-03T16:50:00Z",
          "losses": 38,
          "model": "claude-sonnet-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-2e43b0d163a7f12d",
          "rated_matches": 60,
          "raw_elo_rating": 1285.3975984985518,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "xhigh",
          "repair_status": "first_pass",
          "score": 15.623941414360715,
          "uncertainty": 20.268439966447993,
          "unilateral_faults": 0,
          "wins": 3
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 88,
          "capped_draws": 1,
          "coverage_status": "rated",
          "distinct_rated_opponents": 42,
          "draws": 42,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "xhigh",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-sonnet-5",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 20,
          "model": "claude-sonnet-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-7dde7ed705ef7793",
          "rated_matches": 88,
          "raw_elo_rating": 1575.6075710349296,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "xhigh",
          "repair_status": "first_pass",
          "score": 56.36010974706571,
          "uncertainty": 9.249894000318006,
          "unilateral_faults": 0,
          "wins": 26
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 192,
          "capped_draws": 6,
          "coverage_status": "rated",
          "distinct_rated_opponents": 72,
          "draws": 67,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "xhigh",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-sonnet-5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_7fad32_to_brackets_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-19T15:25:00Z",
          "losses": 53,
          "model": "claude-sonnet-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-d49e8df479ed0377",
          "rated_matches": 192,
          "raw_elo_rating": 1551.8171700743583,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_7fad32_to_brackets_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "xhigh",
          "repair_status": "first_pass",
          "score": 54.97286325089087,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 72
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 90,
          "capped_draws": 8,
          "coverage_status": "rated",
          "distinct_rated_opponents": 42,
          "draws": 31,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-sonnet-5",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 36,
          "model": "claude-sonnet-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-db41eba0d9c3a185",
          "rated_matches": 90,
          "raw_elo_rating": 1455.2008449551374,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 40.02092072410418,
          "uncertainty": 8.664241836095918,
          "unilateral_faults": 0,
          "wins": 23
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 84,
          "capped_draws": 12,
          "coverage_status": "rated",
          "distinct_rated_opponents": 42,
          "draws": 36,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-sonnet-5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 27,
          "model": "claude-sonnet-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-e7d1e6857fc48e7a",
          "rated_matches": 84,
          "raw_elo_rating": 1506.3942752497016,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 46.796831298958985,
          "uncertainty": 10.482614454664043,
          "unilateral_faults": 0,
          "wins": 21
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 32,
          "capped_draws": 1,
          "coverage_status": "rated",
          "distinct_rated_opponents": 16,
          "draws": 16,
          "evaluated_setting_identity": {
            "canonical_provider_route": "unknown_legacy",
            "effective_request_value": "enabled",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "cohere/north-mini-code:free",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 13,
          "model": "cohere/north-mini-code",
          "point_rating_method": "sequential_elo",
          "public_id": "E-0f669ae82234cf76",
          "rated_matches": 32,
          "raw_elo_rating": 1393.6082077811413,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "enabled",
          "repair_status": "repaired",
          "score": 27.856624323434982,
          "uncertainty": 43.288827977848925,
          "unilateral_faults": 0,
          "wins": 3
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 54,
          "capped_draws": 1,
          "coverage_status": "rated",
          "distinct_rated_opponents": 27,
          "draws": 18,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "deepseek/deepseek-v4-flash",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-01T00:15:48Z",
          "losses": 21,
          "model": "deepseek/deepseek-v4-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-32e04fe5ad231857",
          "rated_matches": 54,
          "raw_elo_rating": 1523.0961019109775,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 47.63490899953319,
          "uncertainty": 23.66998624632421,
          "unilateral_faults": 0,
          "wins": 15
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 88,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 44,
          "draws": 40,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "deepseek/deepseek-v4-flash",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 28,
          "model": "deepseek/deepseek-v4-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-ae9d59ec3a8a1d63",
          "rated_matches": 88,
          "raw_elo_rating": 1430.6399776232663,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "repaired",
          "score": 36.61116549844097,
          "uncertainty": 9.249894000318006,
          "unilateral_faults": 0,
          "wins": 20
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 64,
          "capped_draws": 1,
          "coverage_status": "rated",
          "distinct_rated_opponents": 30,
          "draws": 18,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "deepseek/deepseek-v4-pro",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 29,
          "model": "deepseek/deepseek-v4-pro",
          "point_rating_method": "sequential_elo",
          "public_id": "E-f82a334a0fd1fb8e",
          "rated_matches": 64,
          "raw_elo_rating": 1410.1567925431275,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "repaired",
          "score": 32.83797916630326,
          "uncertainty": 18.26736729460423,
          "unilateral_faults": 0,
          "wins": 17
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 78,
          "capped_draws": 2,
          "coverage_status": "rated",
          "distinct_rated_opponents": 37,
          "draws": 56,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "google/gemini-3.5-flash",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 12,
          "model": "google/gemini-3.5-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-46c3bb79de67d970",
          "rated_matches": 78,
          "raw_elo_rating": 1511.688890303186,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "repaired",
          "score": 47.29777519993979,
          "uncertainty": 12.5043950463012,
          "unilateral_faults": 0,
          "wins": 10
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 68,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 34,
          "draws": 30,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "google/gemini-3.5-flash",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 15,
          "model": "google/gemini-3.5-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-8ed795ea8fd1e0aa",
          "rated_matches": 68,
          "raw_elo_rating": 1577.6092570519809,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "repaired",
          "score": 55.84887374161656,
          "uncertainty": 16.4429265428846,
          "unilateral_faults": 0,
          "wins": 23
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 176,
          "capped_draws": 12,
          "coverage_status": "rated",
          "distinct_rated_opponents": 68,
          "draws": 52,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "minimal",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "google/gemini-3.5-flash-lite",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 51,
          "model": "google/gemini-3.5-flash-lite",
          "point_rating_method": "sequential_elo",
          "public_id": "E-28274045fbc35ae9",
          "rated_matches": 176,
          "raw_elo_rating": 1532.6867109455625,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "minimal",
          "repair_status": "repaired",
          "score": 52.19326999050381,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 73
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 140,
          "capped_draws": 4,
          "coverage_status": "rated",
          "distinct_rated_opponents": 48,
          "draws": 23,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "google/gemini-3.5-flash-lite",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 43,
          "model": "google/gemini-3.5-flash-lite",
          "point_rating_method": "sequential_elo",
          "public_id": "E-7ed90f1b43d80cf9",
          "rated_matches": 140,
          "raw_elo_rating": 1664.0889019495849,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "first_pass",
          "score": 69.60101368993861,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 74
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 141,
          "capped_draws": 5,
          "coverage_status": "rated",
          "distinct_rated_opponents": 52,
          "draws": 49,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "google/gemini-3.5-flash-lite",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 59,
          "model": "google/gemini-3.5-flash-lite",
          "point_rating_method": "sequential_elo",
          "public_id": "E-c7e8525629d5d658",
          "rated_matches": 141,
          "raw_elo_rating": 1453.6481623860886,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 40.94884587514523,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 33
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 124,
          "capped_draws": 4,
          "coverage_status": "rated",
          "distinct_rated_opponents": 49,
          "draws": 38,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "google/gemini-3.5-flash-lite",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 52,
          "model": "google/gemini-3.5-flash-lite",
          "point_rating_method": "sequential_elo",
          "public_id": "E-d485651284072880",
          "rated_matches": 124,
          "raw_elo_rating": 1423.3161616673915,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "first_pass",
          "score": 36.51566980579563,
          "uncertainty": 0.9713595499957961,
          "unilateral_faults": 0,
          "wins": 34
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 140,
          "capped_draws": 17,
          "coverage_status": "rated",
          "distinct_rated_opponents": 51,
          "draws": 70,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "google/gemini-3.5-flash-lite",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 50,
          "model": "google/gemini-3.5-flash-lite",
          "point_rating_method": "sequential_elo",
          "public_id": "E-d9a1854998f1794f",
          "rated_matches": 140,
          "raw_elo_rating": 1412.3489003818981,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 35.30645765084414,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 20
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 137,
          "capped_draws": 5,
          "coverage_status": "rated",
          "distinct_rated_opponents": 51,
          "draws": 40,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "google/gemini-3.6-flash",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 35,
          "model": "google/gemini-3.6-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-1d4a922c11c37a8d",
          "rated_matches": 137,
          "raw_elo_rating": 1593.388026886988,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 59.91981623001038,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 62
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 133,
          "capped_draws": 1,
          "coverage_status": "rated",
          "distinct_rated_opponents": 55,
          "draws": 29,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "google/gemini-3.6-flash",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 78,
          "model": "google/gemini-3.6-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-2e4f025f94dafe33",
          "rated_matches": 133,
          "raw_elo_rating": 1403.3327657948776,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 33.95985144610179,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 26
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 163,
          "capped_draws": 4,
          "coverage_status": "rated",
          "distinct_rated_opponents": 65,
          "draws": 41,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "minimal",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "google/gemini-3.6-flash",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 44,
          "model": "google/gemini-3.6-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-6743f1c221046d65",
          "rated_matches": 163,
          "raw_elo_rating": 1539.217433989878,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "minimal",
          "repair_status": "first_pass",
          "score": 52.92370994301519,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 78
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 161,
          "capped_draws": 6,
          "coverage_status": "rated",
          "distinct_rated_opponents": 64,
          "draws": 66,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "minimal",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "google/gemini-3.6-flash",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 46,
          "model": "google/gemini-3.6-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-80b8c1a18d6dd238",
          "rated_matches": 161,
          "raw_elo_rating": 1504.4377526502255,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "minimal",
          "repair_status": "first_pass",
          "score": 48.15948624199781,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 49
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 122,
          "capped_draws": 1,
          "coverage_status": "rated",
          "distinct_rated_opponents": 50,
          "draws": 11,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "google/gemini-3.6-flash",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 23,
          "model": "google/gemini-3.6-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-97580ecf1bd06d40",
          "rated_matches": 122,
          "raw_elo_rating": 1772.0196909880037,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "first_pass",
          "score": 83.98010770719294,
          "uncertainty": 1.3334817333716131,
          "unilateral_faults": 0,
          "wins": 88
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 84,
          "capped_draws": 2,
          "coverage_status": "rated",
          "distinct_rated_opponents": 42,
          "draws": 28,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-4.1",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "omitted",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 31,
          "model": "gpt-4.1",
          "point_rating_method": "sequential_elo",
          "public_id": "E-c7da9914f86ee846",
          "rated_matches": 84,
          "raw_elo_rating": 1521.331600253054,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "omitted",
          "reasoning_setting": "none",
          "repair_status": "repaired",
          "score": 48.831744011327004,
          "uncertainty": 10.482614454664043,
          "unilateral_faults": 0,
          "wins": 25
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 0,
          "capped_draws": 0,
          "coverage_status": "pending",
          "distinct_rated_opponents": 0,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "low",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5",
            "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-21T14:20:15Z",
          "losses": 0,
          "model": "gpt-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-c541923774f0cd7b",
          "rated_matches": 0,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "low",
          "repair_status": "repaired",
          "unilateral_faults": 0,
          "wins": 0
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 77,
          "capped_draws": 5,
          "coverage_status": "rated",
          "distinct_rated_opponents": 34,
          "draws": 29,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 30,
          "model": "gpt-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-cc568b7069d5a0fd",
          "rated_matches": 76,
          "raw_elo_rating": 1455.2318976814317,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "first_pass",
          "score": 39.527524812029206,
          "uncertainty": 13.230288229818967,
          "unilateral_faults": 1,
          "wins": 17
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 64,
          "capped_draws": 1,
          "coverage_status": "rated",
          "distinct_rated_opponents": 31,
          "draws": 35,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 19,
          "model": "gpt-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-e724ba162431d43a",
          "rated_matches": 64,
          "raw_elo_rating": 1402.0902606081052,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 31.739075020104682,
          "uncertainty": 18.26736729460423,
          "unilateral_faults": 0,
          "wins": 10
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 95,
          "capped_draws": 4,
          "coverage_status": "rated",
          "distinct_rated_opponents": 42,
          "draws": 28,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "xhigh",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.4",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 31,
          "model": "gpt-5.4",
          "point_rating_method": "sequential_elo",
          "public_id": "E-09687fbb17ec9c64",
          "rated_matches": 95,
          "raw_elo_rating": 1439.5396369864504,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "xhigh",
          "repair_status": "first_pass",
          "score": 38.03814073039753,
          "uncertainty": 7.281036307982882,
          "unilateral_faults": 0,
          "wins": 36
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 82,
          "capped_draws": 2,
          "coverage_status": "rated",
          "distinct_rated_opponents": 41,
          "draws": 38,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.4",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 25,
          "model": "gpt-5.4",
          "point_rating_method": "sequential_elo",
          "public_id": "E-496f83ad0bd69447",
          "rated_matches": 82,
          "raw_elo_rating": 1430.6751894818985,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 36.41082871103601,
          "uncertainty": 11.132129994845172,
          "unilateral_faults": 0,
          "wins": 19
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 62,
          "capped_draws": 7,
          "coverage_status": "rated",
          "distinct_rated_opponents": 30,
          "draws": 17,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "xhigh",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.4",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 25,
          "model": "gpt-5.4",
          "point_rating_method": "sequential_elo",
          "public_id": "E-4b75acaf58f14113",
          "rated_matches": 60,
          "raw_elo_rating": 1445.9639269862823,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "xhigh",
          "repair_status": "first_pass",
          "score": 37.49790231061323,
          "uncertainty": 20.268439966447993,
          "unilateral_faults": 2,
          "wins": 18
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 94,
          "capped_draws": 6,
          "coverage_status": "rated",
          "distinct_rated_opponents": 42,
          "draws": 48,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.4",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 26,
          "model": "gpt-5.4",
          "point_rating_method": "sequential_elo",
          "public_id": "E-c535d0dba39ffdb8",
          "rated_matches": 94,
          "raw_elo_rating": 1465.4947162156686,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 41.54480799633329,
          "uncertainty": 7.54891760425771,
          "unilateral_faults": 0,
          "wins": 20
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 96,
          "capped_draws": 5,
          "coverage_status": "rated",
          "distinct_rated_opponents": 42,
          "draws": 52,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.4",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 34,
          "model": "gpt-5.4",
          "point_rating_method": "sequential_elo",
          "public_id": "E-ca34006c666b7c30",
          "rated_matches": 96,
          "raw_elo_rating": 1371.9311932402272,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 28.856580393425084,
          "uncertainty": 7.017308256680951,
          "unilateral_faults": 0,
          "wins": 10
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 82,
          "capped_draws": 4,
          "coverage_status": "rated",
          "distinct_rated_opponents": 41,
          "draws": 32,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.4",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 17,
          "model": "gpt-5.4",
          "point_rating_method": "sequential_elo",
          "public_id": "E-ebd456dc6b320c61",
          "rated_matches": 82,
          "raw_elo_rating": 1604.3956609608717,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 60.07677932346456,
          "uncertainty": 11.132129994845172,
          "unilateral_faults": 0,
          "wins": 33
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 84,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 42,
          "draws": 79,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.4-mini",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 4,
          "model": "gpt-5.4-mini",
          "point_rating_method": "sequential_elo",
          "public_id": "E-35117a2e624d7970",
          "rated_matches": 84,
          "raw_elo_rating": 1474.8658260094098,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 42.50170870197985,
          "uncertainty": 10.482614454664043,
          "unilateral_faults": 0,
          "wins": 1
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 85,
          "capped_draws": 12,
          "coverage_status": "rated",
          "distinct_rated_opponents": 42,
          "draws": 49,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.4-mini",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 21,
          "model": "gpt-5.4-mini",
          "point_rating_method": "sequential_elo",
          "public_id": "E-9e39bdd48b7328c7",
          "rated_matches": 85,
          "raw_elo_rating": 1480.1394784776523,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "repaired",
          "score": 43.25460249709266,
          "uncertainty": 10.16638660171921,
          "unilateral_faults": 0,
          "wins": 15
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 90,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 45,
          "draws": 34,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.4-nano",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-09T17:30:50Z",
          "losses": 28,
          "model": "gpt-5.4-nano",
          "point_rating_method": "sequential_elo",
          "public_id": "E-f2a7b43bf689e68e",
          "rated_matches": 90,
          "raw_elo_rating": 1503.4667049734755,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 46.59618183026941,
          "uncertainty": 8.664241836095918,
          "unilateral_faults": 0,
          "wins": 28
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 82,
          "capped_draws": 7,
          "coverage_status": "rated",
          "distinct_rated_opponents": 41,
          "draws": 36,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 28,
          "model": "gpt-5.5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-446036823932df16",
          "rated_matches": 82,
          "raw_elo_rating": 1437.1973645808223,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 37.29934502959449,
          "uncertainty": 11.132129994845172,
          "unilateral_faults": 0,
          "wins": 18
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 76,
          "capped_draws": 7,
          "coverage_status": "rated",
          "distinct_rated_opponents": 38,
          "draws": 37,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 24,
          "model": "gpt-5.5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-c002b0ea38b845f8",
          "rated_matches": 76,
          "raw_elo_rating": 1436.9850240219848,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 37.041752080817375,
          "uncertainty": 13.230288229818967,
          "unilateral_faults": 0,
          "wins": 15
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 83,
          "capped_draws": 3,
          "coverage_status": "rated",
          "distinct_rated_opponents": 39,
          "draws": 30,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "xhigh",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 29,
          "model": "gpt-5.5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-e53a932f820d9724",
          "rated_matches": 82,
          "raw_elo_rating": 1529.349657382233,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "xhigh",
          "repair_status": "first_pass",
          "score": 49.85325759783324,
          "uncertainty": 11.132129994845172,
          "unilateral_faults": 0,
          "wins": 23
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 74,
          "capped_draws": 13,
          "coverage_status": "rated",
          "distinct_rated_opponents": 36,
          "draws": 44,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.6-luna",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-10T05:30:29Z",
          "losses": 17,
          "model": "gpt-5.6-luna",
          "point_rating_method": "sequential_elo",
          "public_id": "E-0300c20cb034e3a4",
          "rated_matches": 74,
          "raw_elo_rating": 1462.3304554695912,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 40.4123073013434,
          "uncertainty": 13.985026918962571,
          "unilateral_faults": 0,
          "wins": 13
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 90,
          "capped_draws": 2,
          "coverage_status": "rated",
          "distinct_rated_opponents": 43,
          "draws": 39,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "xhigh",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.6-luna",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 32,
          "model": "gpt-5.6-luna",
          "point_rating_method": "sequential_elo",
          "public_id": "E-0fbc2c4195016fbe",
          "rated_matches": 90,
          "raw_elo_rating": 1472.744367648308,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "xhigh",
          "repair_status": "first_pass",
          "score": 42.41087590952312,
          "uncertainty": 8.664241836095918,
          "unilateral_faults": 0,
          "wins": 19
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 68,
          "capped_draws": 2,
          "coverage_status": "rated",
          "distinct_rated_opponents": 32,
          "draws": 27,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "xhigh",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.6-luna",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-10T10:07:13Z",
          "losses": 31,
          "model": "gpt-5.6-luna",
          "point_rating_method": "sequential_elo",
          "public_id": "E-3bca3b4e02f2acf9",
          "rated_matches": 68,
          "raw_elo_rating": 1366.0934547211268,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "xhigh",
          "repair_status": "first_pass",
          "score": 27.034062861276098,
          "uncertainty": 16.4429265428846,
          "unilateral_faults": 0,
          "wins": 10
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 94,
          "capped_draws": 4,
          "coverage_status": "rated",
          "distinct_rated_opponents": 42,
          "draws": 51,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.6-luna",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 40,
          "model": "gpt-5.6-luna",
          "point_rating_method": "sequential_elo",
          "public_id": "E-47dd28046ef904f9",
          "rated_matches": 94,
          "raw_elo_rating": 1347.201035529736,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 25.42965253398741,
          "uncertainty": 7.54891760425771,
          "unilateral_faults": 0,
          "wins": 3
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 78,
          "capped_draws": 1,
          "coverage_status": "rated",
          "distinct_rated_opponents": 38,
          "draws": 38,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.6-luna",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-10T05:30:29Z",
          "losses": 19,
          "model": "gpt-5.6-luna",
          "point_rating_method": "sequential_elo",
          "public_id": "E-d192bb239087b778",
          "rated_matches": 78,
          "raw_elo_rating": 1467.7893639049173,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 41.31733999385539,
          "uncertainty": 12.5043950463012,
          "unilateral_faults": 0,
          "wins": 21
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 93,
          "capped_draws": 3,
          "coverage_status": "rated",
          "distinct_rated_opponents": 43,
          "draws": 27,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.6-luna",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 44,
          "model": "gpt-5.6-luna",
          "point_rating_method": "sequential_elo",
          "public_id": "E-d4115a59dfe21984",
          "rated_matches": 93,
          "raw_elo_rating": 1441.308968688837,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 38.22032267709648,
          "uncertainty": 7.821062312939668,
          "unilateral_faults": 0,
          "wins": 22
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 70,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 30,
          "draws": 7,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "xhigh",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.6-sol",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-10T05:30:29Z",
          "losses": 26,
          "model": "gpt-5.6-sol",
          "point_rating_method": "sequential_elo",
          "public_id": "E-2ac4e83a1b9ba989",
          "rated_matches": 70,
          "raw_elo_rating": 1625.9039362576423,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "xhigh",
          "repair_status": "first_pass",
          "score": 62.521116224377955,
          "uncertainty": 15.58908290969266,
          "unilateral_faults": 0,
          "wins": 37
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 82,
          "capped_draws": 15,
          "coverage_status": "rated",
          "distinct_rated_opponents": 41,
          "draws": 42,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.6-sol",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-10T05:30:29Z",
          "losses": 25,
          "model": "gpt-5.6-sol",
          "point_rating_method": "sequential_elo",
          "public_id": "E-527999604d620080",
          "rated_matches": 82,
          "raw_elo_rating": 1444.8744235238303,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 38.34519124591633,
          "uncertainty": 11.132129994845172,
          "unilateral_faults": 0,
          "wins": 15
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 92,
          "capped_draws": 7,
          "coverage_status": "rated",
          "distinct_rated_opponents": 43,
          "draws": 35,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.6-sol",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 19,
          "model": "gpt-5.6-sol",
          "point_rating_method": "sequential_elo",
          "public_id": "E-79655cafc06e8943",
          "rated_matches": 92,
          "raw_elo_rating": 1546.3926522758095,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 52.50574288116246,
          "uncertainty": 8.09758473652126,
          "unilateral_faults": 0,
          "wins": 38
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 90,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 42,
          "draws": 9,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.6-sol",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 25,
          "model": "gpt-5.6-sol",
          "point_rating_method": "sequential_elo",
          "public_id": "E-826bd7fcad40bd61",
          "rated_matches": 90,
          "raw_elo_rating": 1642.3853735340704,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 65.52108067097569,
          "uncertainty": 8.664241836095918,
          "unilateral_faults": 0,
          "wins": 56
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 60,
          "capped_draws": 2,
          "coverage_status": "rated",
          "distinct_rated_opponents": 30,
          "draws": 13,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.6-sol",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-10T05:30:29Z",
          "losses": 16,
          "model": "gpt-5.6-sol",
          "point_rating_method": "sequential_elo",
          "public_id": "E-b741de451c385e8e",
          "rated_matches": 60,
          "raw_elo_rating": 1556.5990433024108,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 52.56973107349277,
          "uncertainty": 20.268439966447993,
          "unilateral_faults": 0,
          "wins": 31
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 92,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 42,
          "draws": 1,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "xhigh",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.6-sol",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 6,
          "model": "gpt-5.6-sol",
          "point_rating_method": "sequential_elo",
          "public_id": "E-d2ec4e4765cdd61a",
          "rated_matches": 92,
          "raw_elo_rating": 1868.3709719929363,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "xhigh",
          "repair_status": "first_pass",
          "score": 96.368869361455,
          "uncertainty": 8.09758473652126,
          "unilateral_faults": 0,
          "wins": 85
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 62,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 29,
          "draws": 15,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "xhigh",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.6-terra",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-10T05:30:29Z",
          "losses": 16,
          "model": "gpt-5.6-terra",
          "point_rating_method": "sequential_elo",
          "public_id": "E-39e763b7d49209b4",
          "rated_matches": 62,
          "raw_elo_rating": 1614.760774095997,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "xhigh",
          "repair_status": "repaired",
          "score": 60.60474629403735,
          "uncertainty": 19.244078834871203,
          "unilateral_faults": 0,
          "wins": 31
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 80,
          "capped_draws": 9,
          "coverage_status": "rated",
          "distinct_rated_opponents": 40,
          "draws": 36,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.6-terra",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-10T10:07:13Z",
          "losses": 24,
          "model": "gpt-5.6-terra",
          "point_rating_method": "sequential_elo",
          "public_id": "E-c2f0f8f062659e83",
          "rated_matches": 80,
          "raw_elo_rating": 1515.2761169916803,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 47.862625672133966,
          "uncertainty": 11.805555555555554,
          "unilateral_faults": 0,
          "wins": 20
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 78,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 39,
          "draws": 39,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.6-terra",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-10T05:30:29Z",
          "losses": 25,
          "model": "gpt-5.6-terra",
          "point_rating_method": "sequential_elo",
          "public_id": "E-e44c62bb88a3042a",
          "rated_matches": 78,
          "raw_elo_rating": 1480.6473394621028,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 43.06898280210667,
          "uncertainty": 12.5043950463012,
          "unilateral_faults": 0,
          "wins": 14
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 102,
          "capped_draws": 2,
          "coverage_status": "rated",
          "distinct_rated_opponents": 40,
          "draws": 40,
          "evaluated_setting_identity": {
            "canonical_provider_route": "unknown_legacy",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "inclusionai/ling-3.0-flash:free",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 47,
          "model": "inclusionai/ling-3.0-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-2524de3c7d4a81b7",
          "rated_matches": 102,
          "raw_elo_rating": 1305.971312261028,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "none",
          "repair_status": "repaired",
          "score": 20.034429808491304,
          "uncertainty": 5.516463908214657,
          "unilateral_faults": 0,
          "wins": 15
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 98,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 39,
          "draws": 47,
          "evaluated_setting_identity": {
            "canonical_provider_route": "unknown_legacy",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "inclusionai/ling-3.0-flash:free",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 30,
          "model": "inclusionai/ling-3.0-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-641ddca04b054d56",
          "rated_matches": 98,
          "raw_elo_rating": 1417.3184613791018,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "none",
          "repair_status": "repaired",
          "score": 35.09586303490573,
          "uncertainty": 6.501890762960602,
          "unilateral_faults": 0,
          "wins": 21
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 80,
          "capped_draws": 5,
          "coverage_status": "rated",
          "distinct_rated_opponents": 38,
          "draws": 35,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "meituan/longcat-2.0",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 33,
          "model": "meituan/longcat-2.0",
          "point_rating_method": "sequential_elo",
          "public_id": "E-198e8ddfe9f7ce20",
          "rated_matches": 80,
          "raw_elo_rating": 1320.9190075493696,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "none",
          "repair_status": "repaired",
          "score": 21.38534458904165,
          "uncertainty": 11.805555555555554,
          "unilateral_faults": 0,
          "wins": 12
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 86,
          "capped_draws": 9,
          "coverage_status": "rated",
          "distinct_rated_opponents": 41,
          "draws": 39,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "meituan/longcat-2.0",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 21,
          "model": "meituan/longcat-2.0",
          "point_rating_method": "sequential_elo",
          "public_id": "E-84709c769628f9a2",
          "rated_matches": 86,
          "raw_elo_rating": 1440.8637202178857,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 37.93793137950897,
          "uncertainty": 9.855626741889738,
          "unilateral_faults": 0,
          "wins": 26
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 142,
          "capped_draws": 19,
          "coverage_status": "rated",
          "distinct_rated_opponents": 50,
          "draws": 62,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "enabled",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "meituan/longcat-2.0",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 39,
          "model": "meituan/longcat-2.0",
          "point_rating_method": "sequential_elo",
          "public_id": "E-d3a5befe76215b48",
          "rated_matches": 142,
          "raw_elo_rating": 1476.9131306078064,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "enabled",
          "repair_status": "first_pass",
          "score": 44.134251044046394,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 41
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 92,
          "capped_draws": 1,
          "coverage_status": "rated",
          "distinct_rated_opponents": 43,
          "draws": 12,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "minimal",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "meta/muse-spark-1.2",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-08-13T16:58:34Z",
          "losses": 36,
          "model": "meta/muse-spark-1.2",
          "point_rating_method": "sequential_elo",
          "public_id": "E-0ed752547c3943ba",
          "rated_matches": 92,
          "raw_elo_rating": 1549.3266540892673,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "minimal",
          "repair_status": "first_pass",
          "score": 52.90544213032362,
          "uncertainty": 8.09758473652126,
          "unilateral_faults": 0,
          "wins": 44
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 94,
          "capped_draws": 8,
          "coverage_status": "rated",
          "distinct_rated_opponents": 43,
          "draws": 29,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "meta/muse-spark-1.2",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-08-13T16:58:34Z",
          "losses": 30,
          "model": "meta/muse-spark-1.2",
          "point_rating_method": "sequential_elo",
          "public_id": "E-4d97f32199e2a33d",
          "rated_matches": 94,
          "raw_elo_rating": 1547.3955110326083,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 52.70215835783597,
          "uncertainty": 7.54891760425771,
          "unilateral_faults": 0,
          "wins": 35
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 92,
          "capped_draws": 6,
          "coverage_status": "rated",
          "distinct_rated_opponents": 42,
          "draws": 15,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "xhigh",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "meta/muse-spark-1.2",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-08-13T16:58:34Z",
          "losses": 34,
          "model": "meta/muse-spark-1.2",
          "point_rating_method": "sequential_elo",
          "public_id": "E-967e1c4101f2c062",
          "rated_matches": 92,
          "raw_elo_rating": 1518.9551554503532,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "xhigh",
          "repair_status": "first_pass",
          "score": 48.767930985582225,
          "uncertainty": 8.09758473652126,
          "unilateral_faults": 0,
          "wins": 43
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 92,
          "capped_draws": 1,
          "coverage_status": "rated",
          "distinct_rated_opponents": 46,
          "draws": 34,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "minimax/minimax-m3",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 26,
          "model": "minimax/minimax-m3",
          "point_rating_method": "sequential_elo",
          "public_id": "E-44cc758f104a74ab",
          "rated_matches": 92,
          "raw_elo_rating": 1464.257046359489,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 41.31640418901639,
          "uncertainty": 8.09758473652126,
          "unilateral_faults": 0,
          "wins": 32
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 158,
          "capped_draws": 3,
          "coverage_status": "rated",
          "distinct_rated_opponents": 67,
          "draws": 40,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "low",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "moonshotai/kimi-k3",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T14:00:00Z",
          "losses": 40,
          "model": "moonshotai/kimi-k3",
          "point_rating_method": "sequential_elo",
          "public_id": "E-09859be1b47131a0",
          "rated_matches": 158,
          "raw_elo_rating": 1571.4990999527986,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "low",
          "repair_status": "first_pass",
          "score": 57.255056886144494,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 78
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 120,
          "capped_draws": 4,
          "coverage_status": "rated",
          "distinct_rated_opponents": 48,
          "draws": 57,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "max",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "moonshotai/kimi-k3",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T14:00:00Z",
          "losses": 35,
          "model": "moonshotai/kimi-k3",
          "point_rating_method": "sequential_elo",
          "public_id": "E-8f139a9e4d538859",
          "rated_matches": 120,
          "raw_elo_rating": 1438.701374575963,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "max",
          "repair_status": "first_pass",
          "score": 38.53169274626354,
          "uncertainty": 1.7045454545454586,
          "unilateral_faults": 0,
          "wins": 28
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 134,
          "capped_draws": 3,
          "coverage_status": "rated",
          "distinct_rated_opponents": 52,
          "draws": 52,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "moonshotai/kimi-k3",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T14:00:00Z",
          "losses": 21,
          "model": "moonshotai/kimi-k3",
          "point_rating_method": "sequential_elo",
          "public_id": "E-980b1f419104e27a",
          "rated_matches": 134,
          "raw_elo_rating": 1644.1494064849203,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "first_pass",
          "score": 66.78378455408968,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 61
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 76,
          "capped_draws": 5,
          "coverage_status": "rated",
          "distinct_rated_opponents": 35,
          "draws": 35,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "enabled",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "nex-agi/nex-n2-pro",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 27,
          "model": "nex-agi/nex-n2-pro",
          "point_rating_method": "sequential_elo",
          "public_id": "E-57ad2863cbf32d58",
          "rated_matches": 76,
          "raw_elo_rating": 1414.8192171011551,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "enabled",
          "repair_status": "repaired",
          "score": 34.022102828158765,
          "uncertainty": 13.230288229818967,
          "unilateral_faults": 0,
          "wins": 14
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 68,
          "capped_draws": 7,
          "coverage_status": "rated",
          "distinct_rated_opponents": 32,
          "draws": 43,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "nex-agi/nex-n2-pro",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 15,
          "model": "nex-agi/nex-n2-pro",
          "point_rating_method": "sequential_elo",
          "public_id": "E-a05d4cef5f788f16",
          "rated_matches": 68,
          "raw_elo_rating": 1447.1051582810692,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "none",
          "repair_status": "repaired",
          "score": 38.07029226565205,
          "uncertainty": 16.4429265428846,
          "unilateral_faults": 0,
          "wins": 10
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 50,
          "capped_draws": 6,
          "coverage_status": "rated",
          "distinct_rated_opponents": 25,
          "draws": 38,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "nvidia/nemotron-3-ultra-550b-a55b",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 9,
          "model": "nvidia/nemotron-3-ultra-550b-a55b",
          "point_rating_method": "sequential_elo",
          "public_id": "E-eb6e8a61f620acfd",
          "rated_matches": 50,
          "raw_elo_rating": 1393.790497688098,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "repaired",
          "score": 29.736891928612994,
          "uncertainty": 26.264004201400486,
          "unilateral_faults": 0,
          "wins": 3
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 136,
          "capped_draws": 1,
          "coverage_status": "rated",
          "distinct_rated_opponents": 47,
          "draws": 49,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "o3",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-03T16:00:00Z",
          "losses": 55,
          "model": "o3",
          "point_rating_method": "sequential_elo",
          "public_id": "E-9f7b8b1adc2ddba7",
          "rated_matches": 134,
          "raw_elo_rating": 1439.0846957731926,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "first_pass",
          "score": 38.84780628544275,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 30
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 66,
          "capped_draws": 8,
          "coverage_status": "rated",
          "distinct_rated_opponents": 33,
          "draws": 43,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "openai/gpt-oss-120b",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 13,
          "model": "openai/gpt-oss-120b",
          "point_rating_method": "sequential_elo",
          "public_id": "E-87b4bd61da369b42",
          "rated_matches": 66,
          "raw_elo_rating": 1409.558557661116,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "repaired",
          "score": 32.858125032877226,
          "uncertainty": 17.33472217815261,
          "unilateral_faults": 0,
          "wins": 10
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 152,
          "capped_draws": 7,
          "coverage_status": "rated",
          "distinct_rated_opponents": 62,
          "draws": 63,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "low",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "openai/gpt-oss-120b",
            "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-21T14:20:15Z",
          "losses": 78,
          "model": "openai/gpt-oss-120b",
          "point_rating_method": "sequential_elo",
          "public_id": "E-c90a449ff5e7b79a",
          "rated_matches": 152,
          "raw_elo_rating": 1273.1146500874393,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "low",
          "repair_status": "first_pass",
          "score": 16.522204329731178,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 11
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 154,
          "capped_draws": 7,
          "coverage_status": "rated",
          "distinct_rated_opponents": 58,
          "draws": 87,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "enabled",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "poolside/laguna-s-2.1",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 50,
          "model": "poolside/laguna-s-2.1",
          "point_rating_method": "sequential_elo",
          "public_id": "E-08762a3df1a52f6b",
          "rated_matches": 154,
          "raw_elo_rating": 1404.8379963900634,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "enabled",
          "repair_status": "first_pass",
          "score": 34.49539831171606,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 17
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 163,
          "capped_draws": 3,
          "coverage_status": "rated",
          "distinct_rated_opponents": 68,
          "draws": 69,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "poolside/laguna-s-2.1",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 49,
          "model": "poolside/laguna-s-2.1",
          "point_rating_method": "sequential_elo",
          "public_id": "E-7acc466aeae25d41",
          "rated_matches": 163,
          "raw_elo_rating": 1468.9437116258425,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 43.35031638346527,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 45
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 88,
          "capped_draws": 5,
          "coverage_status": "rated",
          "distinct_rated_opponents": 44,
          "draws": 40,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "poolside/laguna-s-2.1",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 28,
          "model": "poolside/laguna-s-2.1",
          "point_rating_method": "sequential_elo",
          "public_id": "E-91efdb0c216f8504",
          "rated_matches": 88,
          "raw_elo_rating": 1429.8575467811165,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "none",
          "repair_status": "repaired",
          "score": 36.50457489624934,
          "uncertainty": 9.249894000318006,
          "unilateral_faults": 0,
          "wins": 20
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 164,
          "capped_draws": 17,
          "coverage_status": "rated",
          "distinct_rated_opponents": 59,
          "draws": 46,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "enabled",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "poolside/laguna-s-2.1",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 73,
          "model": "poolside/laguna-s-2.1",
          "point_rating_method": "sequential_elo",
          "public_id": "E-936fb7956df3d03b",
          "rated_matches": 164,
          "raw_elo_rating": 1409.001159135909,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "enabled",
          "repair_status": "repaired",
          "score": 35.19725261289695,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 45
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 68,
          "capped_draws": 6,
          "coverage_status": "rated",
          "distinct_rated_opponents": 32,
          "draws": 52,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "qwen/qwen3.7-max",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 10,
          "model": "qwen/qwen3.7-max",
          "point_rating_method": "sequential_elo",
          "public_id": "E-3325ebad2ef000c1",
          "rated_matches": 68,
          "raw_elo_rating": 1426.0472522295584,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 35.201572417188274,
          "uncertainty": 16.4429265428846,
          "unilateral_faults": 0,
          "wins": 6
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 16,
          "capped_draws": 1,
          "coverage_status": "under_covered",
          "distinct_rated_opponents": 9,
          "draws": 6,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "qwen/qwen3.8-max",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 5,
          "model": "qwen/qwen3.8-max",
          "point_rating_method": "sequential_elo",
          "public_id": "E-5481497913530d6b",
          "rated_matches": 16,
          "raw_elo_rating": 1501.4910334028175,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 38.823095003355,
          "uncertainty": 77.5178125181665,
          "unilateral_faults": 0,
          "wins": 5
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 17,
          "capped_draws": 0,
          "coverage_status": "under_covered",
          "distinct_rated_opponents": 9,
          "draws": 1,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "xhigh",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "qwen/qwen3.8-max",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 7,
          "model": "qwen/qwen3.8-max",
          "point_rating_method": "sequential_elo",
          "public_id": "E-d2322903ed52a2c3",
          "rated_matches": 17,
          "raw_elo_rating": 1520.0917022516862,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "xhigh",
          "repair_status": "first_pass",
          "score": 41.72942915084835,
          "uncertainty": 74.10113019775793,
          "unilateral_faults": 0,
          "wins": 9
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 15,
          "capped_draws": 2,
          "coverage_status": "under_covered",
          "distinct_rated_opponents": 9,
          "draws": 7,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "minimal",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "qwen/qwen3.8-max",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 7,
          "model": "qwen/qwen3.8-max",
          "point_rating_method": "sequential_elo",
          "public_id": "E-da44e2f9cd203f91",
          "rated_matches": 15,
          "raw_elo_rating": 1440.2371045770194,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "minimal",
          "repair_status": "first_pass",
          "score": 30.071719571532732,
          "uncertainty": 81.25,
          "unilateral_faults": 0,
          "wins": 1
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 0,
          "capped_draws": 0,
          "coverage_status": "pending",
          "distinct_rated_opponents": 0,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "stealth/ox-alpha",
            "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-08-21T22:22:23Z",
          "losses": 0,
          "model": "stealth/ox-alpha",
          "point_rating_method": "sequential_elo",
          "public_id": "E-01ad48d5f93e32a0",
          "rated_matches": 0,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "first_pass",
          "unilateral_faults": 0,
          "wins": 0
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 0,
          "capped_draws": 0,
          "coverage_status": "pending",
          "distinct_rated_opponents": 0,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "stealth/ox-alpha",
            "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-08-21T20:50:14Z",
          "losses": 0,
          "model": "stealth/ox-alpha",
          "point_rating_method": "sequential_elo",
          "public_id": "E-14673673976cc3eb",
          "rated_matches": 0,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "first_pass",
          "unilateral_faults": 0,
          "wins": 0
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 0,
          "capped_draws": 0,
          "coverage_status": "pending",
          "distinct_rated_opponents": 0,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "low",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "stealth/ox-alpha",
            "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-08-21T20:50:14Z",
          "losses": 0,
          "model": "stealth/ox-alpha",
          "point_rating_method": "sequential_elo",
          "public_id": "E-213cbd917b9e3b75",
          "rated_matches": 0,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "low",
          "repair_status": "first_pass",
          "unilateral_faults": 0,
          "wins": 0
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 0,
          "capped_draws": 0,
          "coverage_status": "pending",
          "distinct_rated_opponents": 0,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "max",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "stealth/ox-alpha",
            "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-08-21T22:22:23Z",
          "losses": 0,
          "model": "stealth/ox-alpha",
          "point_rating_method": "sequential_elo",
          "public_id": "E-41517f1495980c1f",
          "rated_matches": 0,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "max",
          "repair_status": "first_pass",
          "unilateral_faults": 0,
          "wins": 0
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 12,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 6,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "stealth/ox-alpha",
            "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-08-22T00:27:26Z",
          "losses": 1,
          "model": "stealth/ox-alpha",
          "point_rating_method": "sequential_elo",
          "public_id": "E-449a1a79eee8c26f",
          "rated_matches": 12,
          "raw_elo_rating": 1613.7046840011644,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "first_pass",
          "score": 52.212856458233006,
          "uncertainty": 94.92504905630729,
          "unilateral_faults": 0,
          "wins": 11
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 15,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 6,
          "draws": 3,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "max",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "stealth/ox-alpha",
            "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-08-22T00:27:26Z",
          "losses": 4,
          "model": "stealth/ox-alpha",
          "point_rating_method": "sequential_elo",
          "public_id": "E-463b747dfc9e53e2",
          "rated_matches": 11,
          "raw_elo_rating": 1500.5302324598551,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "max",
          "repair_status": "first_pass",
          "score": 36.177969730843834,
          "uncertainty": 100.0,
          "unilateral_faults": 4,
          "wins": 4
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 13,
          "capped_draws": 1,
          "coverage_status": "rated",
          "distinct_rated_opponents": 6,
          "draws": 5,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "stealth/ox-alpha",
            "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-08-22T00:27:26Z",
          "losses": 5,
          "model": "stealth/ox-alpha",
          "point_rating_method": "sequential_elo",
          "public_id": "E-7aeb7747204eb58b",
          "rated_matches": 12,
          "raw_elo_rating": 1461.1114825492753,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "first_pass",
          "score": 31.425075152965995,
          "uncertainty": 94.92504905630729,
          "unilateral_faults": 0,
          "wins": 2
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 0,
          "capped_draws": 0,
          "coverage_status": "pending",
          "distinct_rated_opponents": 0,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "stealth/ox-alpha",
            "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-08-21T20:50:14Z",
          "losses": 0,
          "model": "stealth/ox-alpha",
          "point_rating_method": "sequential_elo",
          "public_id": "E-7c7b61f033bf610f",
          "rated_matches": 0,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "repaired",
          "unilateral_faults": 0,
          "wins": 0
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 12,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 6,
          "draws": 7,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "max",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "stealth/ox-alpha",
            "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-08-22T00:27:26Z",
          "losses": 2,
          "model": "stealth/ox-alpha",
          "point_rating_method": "sequential_elo",
          "public_id": "E-82c718cb6269d828",
          "rated_matches": 12,
          "raw_elo_rating": 1516.6704005400268,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "max",
          "repair_status": "repaired",
          "score": 38.993869999393986,
          "uncertainty": 94.92504905630729,
          "unilateral_faults": 0,
          "wins": 3
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 0,
          "capped_draws": 0,
          "coverage_status": "pending",
          "distinct_rated_opponents": 0,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "max",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "stealth/ox-alpha",
            "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-08-21T22:22:23Z",
          "losses": 0,
          "model": "stealth/ox-alpha",
          "point_rating_method": "sequential_elo",
          "public_id": "E-88583455f6e29fdd",
          "rated_matches": 0,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "max",
          "repair_status": "first_pass",
          "unilateral_faults": 0,
          "wins": 0
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 0,
          "capped_draws": 0,
          "coverage_status": "pending",
          "distinct_rated_opponents": 0,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "low",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "stealth/ox-alpha",
            "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-08-21T20:50:14Z",
          "losses": 0,
          "model": "stealth/ox-alpha",
          "point_rating_method": "sequential_elo",
          "public_id": "E-8ba70fb303bf5927",
          "rated_matches": 0,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "low",
          "repair_status": "repaired",
          "unilateral_faults": 0,
          "wins": 0
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 13,
          "capped_draws": 1,
          "coverage_status": "rated",
          "distinct_rated_opponents": 6,
          "draws": 5,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "low",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "stealth/ox-alpha",
            "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-08-22T00:27:26Z",
          "losses": 5,
          "model": "stealth/ox-alpha",
          "point_rating_method": "sequential_elo",
          "public_id": "E-91f209f8f1ca6da4",
          "rated_matches": 12,
          "raw_elo_rating": 1465.647565832718,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "low",
          "repair_status": "repaired",
          "score": 32.043026060224584,
          "uncertainty": 94.92504905630729,
          "unilateral_faults": 1,
          "wins": 2
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 0,
          "capped_draws": 0,
          "coverage_status": "pending",
          "distinct_rated_opponents": 0,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "low",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "stealth/ox-alpha",
            "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-08-21T22:22:23Z",
          "losses": 0,
          "model": "stealth/ox-alpha",
          "point_rating_method": "sequential_elo",
          "public_id": "E-9f1a927cfaf6d760",
          "rated_matches": 0,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "low",
          "repair_status": "repaired",
          "unilateral_faults": 0,
          "wins": 0
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 0,
          "capped_draws": 0,
          "coverage_status": "pending",
          "distinct_rated_opponents": 0,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "low",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "stealth/ox-alpha",
            "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-08-21T22:22:23Z",
          "losses": 0,
          "model": "stealth/ox-alpha",
          "point_rating_method": "sequential_elo",
          "public_id": "E-a03a524a03b22367",
          "rated_matches": 0,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "low",
          "repair_status": "first_pass",
          "unilateral_faults": 0,
          "wins": 0
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 0,
          "capped_draws": 0,
          "coverage_status": "pending",
          "distinct_rated_opponents": 0,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "low",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "stealth/ox-alpha",
            "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-08-21T20:50:14Z",
          "losses": 0,
          "model": "stealth/ox-alpha",
          "point_rating_method": "sequential_elo",
          "public_id": "E-a4422e1fd753be13",
          "rated_matches": 0,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "low",
          "repair_status": "first_pass",
          "unilateral_faults": 0,
          "wins": 0
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 15,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 6,
          "draws": 6,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "low",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "stealth/ox-alpha",
            "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-08-22T00:27:26Z",
          "losses": 5,
          "model": "stealth/ox-alpha",
          "point_rating_method": "sequential_elo",
          "public_id": "E-acf0cd8991a453ef",
          "rated_matches": 11,
          "raw_elo_rating": 1434.814076597161,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "low",
          "repair_status": "first_pass",
          "score": 27.225453738660264,
          "uncertainty": 100.0,
          "unilateral_faults": 0,
          "wins": 0
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 0,
          "capped_draws": 0,
          "coverage_status": "pending",
          "distinct_rated_opponents": 0,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "stealth/ox-alpha",
            "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-08-21T22:22:23Z",
          "losses": 0,
          "model": "stealth/ox-alpha",
          "point_rating_method": "sequential_elo",
          "public_id": "E-b1c61a0495f26448",
          "rated_matches": 0,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "first_pass",
          "unilateral_faults": 0,
          "wins": 0
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 0,
          "capped_draws": 0,
          "coverage_status": "pending",
          "distinct_rated_opponents": 0,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "stealth/ox-alpha",
            "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-08-21T22:22:23Z",
          "losses": 0,
          "model": "stealth/ox-alpha",
          "point_rating_method": "sequential_elo",
          "public_id": "E-d5879b5524510a71",
          "rated_matches": 0,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "first_pass",
          "unilateral_faults": 0,
          "wins": 0
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 12,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 6,
          "draws": 8,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "max",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "stealth/ox-alpha",
            "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-08-22T00:27:26Z",
          "losses": 2,
          "model": "stealth/ox-alpha",
          "point_rating_method": "sequential_elo",
          "public_id": "E-de081f655675d088",
          "rated_matches": 12,
          "raw_elo_rating": 1507.5215580197994,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "max",
          "repair_status": "first_pass",
          "score": 37.74752261499379,
          "uncertainty": 94.92504905630729,
          "unilateral_faults": 0,
          "wins": 2
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 0,
          "capped_draws": 0,
          "coverage_status": "pending",
          "distinct_rated_opponents": 0,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "low",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "stealth/ox-alpha",
            "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-08-21T22:22:23Z",
          "losses": 0,
          "model": "stealth/ox-alpha",
          "point_rating_method": "sequential_elo",
          "public_id": "E-eb6d338f3b9c76c6",
          "rated_matches": 0,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "low",
          "repair_status": "first_pass",
          "unilateral_faults": 0,
          "wins": 0
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 88,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 43,
          "draws": 30,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "tencent/hy3-preview",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 28,
          "model": "tencent/hy3-preview",
          "point_rating_method": "sequential_elo",
          "public_id": "E-2346cd049910cc0a",
          "rated_matches": 88,
          "raw_elo_rating": 1444.882558264278,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 38.551433143204484,
          "uncertainty": 9.249894000318006,
          "unilateral_faults": 0,
          "wins": 30
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 134,
          "capped_draws": 3,
          "coverage_status": "rated",
          "distinct_rated_opponents": 51,
          "draws": 25,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "thinkingmachines/inkling",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 37,
          "model": "thinkingmachines/inkling",
          "point_rating_method": "sequential_elo",
          "public_id": "E-77829668b3641188",
          "rated_matches": 134,
          "raw_elo_rating": 1556.1129209687915,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 54.7905686677935,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 72
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 80,
          "capped_draws": 6,
          "coverage_status": "rated",
          "distinct_rated_opponents": 38,
          "draws": 44,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "thinkingmachines/inkling",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 18,
          "model": "thinkingmachines/inkling",
          "point_rating_method": "sequential_elo",
          "public_id": "E-78048b7c08122f1c",
          "rated_matches": 80,
          "raw_elo_rating": 1424.341435088916,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "repaired",
          "score": 35.47458831219506,
          "uncertainty": 11.805555555555554,
          "unilateral_faults": 0,
          "wins": 18
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 88,
          "capped_draws": 10,
          "coverage_status": "rated",
          "distinct_rated_opponents": 44,
          "draws": 37,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "thinkingmachines/inkling",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 19,
          "model": "thinkingmachines/inkling",
          "point_rating_method": "sequential_elo",
          "public_id": "E-adf1f0bb193bd39b",
          "rated_matches": 88,
          "raw_elo_rating": 1603.6268172129808,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 60.17717339305919,
          "uncertainty": 9.249894000318006,
          "unilateral_faults": 0,
          "wins": 32
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 124,
          "capped_draws": 6,
          "coverage_status": "rated",
          "distinct_rated_opponents": 48,
          "draws": 50,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "max",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "thinkingmachines/inkling",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 41,
          "model": "thinkingmachines/inkling",
          "point_rating_method": "sequential_elo",
          "public_id": "E-f9259c1ced4fba75",
          "rated_matches": 124,
          "raw_elo_rating": 1455.6626650012568,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "max",
          "repair_status": "first_pass",
          "score": 40.92223596271898,
          "uncertainty": 0.9713595499957961,
          "unilateral_faults": 0,
          "wins": 33
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 18,
          "capped_draws": 1,
          "coverage_status": "under_covered",
          "distinct_rated_opponents": 8,
          "draws": 4,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "max",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "thinkingmachines/inkling-small",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 5,
          "model": "thinkingmachines/inkling-small",
          "point_rating_method": "sequential_elo",
          "public_id": "E-5ee731d79dc75fa4",
          "rated_matches": 18,
          "raw_elo_rating": 1545.532411443232,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "max",
          "repair_status": "first_pass",
          "score": 45.53778410260007,
          "uncertainty": 70.95786693528086,
          "unilateral_faults": 0,
          "wins": 9
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 16,
          "capped_draws": 0,
          "coverage_status": "under_covered",
          "distinct_rated_opponents": 9,
          "draws": 6,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "thinkingmachines/inkling-small",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 4,
          "model": "thinkingmachines/inkling-small",
          "point_rating_method": "sequential_elo",
          "public_id": "E-7a0adb70b85361e4",
          "rated_matches": 16,
          "raw_elo_rating": 1518.121643907326,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 41.08868410464794,
          "uncertainty": 77.5178125181665,
          "unilateral_faults": 0,
          "wins": 6
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 17,
          "capped_draws": 0,
          "coverage_status": "under_covered",
          "distinct_rated_opponents": 9,
          "draws": 6,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "thinkingmachines/inkling-small",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 5,
          "model": "thinkingmachines/inkling-small",
          "point_rating_method": "sequential_elo",
          "public_id": "E-a17a40d8dd4cbb06",
          "rated_matches": 17,
          "raw_elo_rating": 1509.8258524700977,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "repaired",
          "score": 40.330911797900164,
          "uncertainty": 74.10113019775793,
          "unilateral_faults": 0,
          "wins": 6
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 162,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 64,
          "draws": 42,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "low",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "x-ai/grok-4.5",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T14:00:00Z",
          "losses": 111,
          "model": "x-ai/grok-4.5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-02f7e54245bd5c85",
          "rated_matches": 162,
          "raw_elo_rating": 1150.82535220259,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "low",
          "repair_status": "repaired",
          "score": 0.0,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 9
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 158,
          "capped_draws": 12,
          "coverage_status": "rated",
          "distinct_rated_opponents": 57,
          "draws": 68,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "x-ai/grok-4.5",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T14:00:00Z",
          "losses": 56,
          "model": "x-ai/grok-4.5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-c0c60ca46f3ce498",
          "rated_matches": 158,
          "raw_elo_rating": 1453.345041387723,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "first_pass",
          "score": 41.15892215398935,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 34
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 78,
          "capped_draws": 1,
          "coverage_status": "rated",
          "distinct_rated_opponents": 39,
          "draws": 28,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "x-ai/grok-4.5",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T14:00:00Z",
          "losses": 26,
          "model": "x-ai/grok-4.5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-cbed46472ce4dd05",
          "rated_matches": 78,
          "raw_elo_rating": 1508.9890080189186,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 46.92997006877206,
          "uncertainty": 12.5043950463012,
          "unilateral_faults": 0,
          "wins": 24
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 70,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 33,
          "draws": 32,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "enabled",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "x-ai/grok-build-0.1",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 20,
          "model": "x-ai/grok-build-0.1",
          "point_rating_method": "sequential_elo",
          "public_id": "E-2a93343a8a88fd59",
          "rated_matches": 70,
          "raw_elo_rating": 1411.5993597267618,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "enabled",
          "repair_status": "repaired",
          "score": 33.32639046166839,
          "uncertainty": 15.58908290969266,
          "unilateral_faults": 0,
          "wins": 18
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 88,
          "capped_draws": 1,
          "coverage_status": "rated",
          "distinct_rated_opponents": 44,
          "draws": 41,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "xiaomi/mimo-v2.5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 26,
          "model": "xiaomi/mimo-v2.5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-b10e12eb6aef112e",
          "rated_matches": 88,
          "raw_elo_rating": 1494.2810908524089,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 45.280998303857686,
          "uncertainty": 9.249894000318006,
          "unilateral_faults": 0,
          "wins": 21
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 70,
          "capped_draws": 6,
          "coverage_status": "rated",
          "distinct_rated_opponents": 33,
          "draws": 41,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "xiaomi/mimo-v2.5-pro",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 15,
          "model": "xiaomi/mimo-v2.5-pro",
          "point_rating_method": "sequential_elo",
          "public_id": "E-b0948c64dddf57ad",
          "rated_matches": 70,
          "raw_elo_rating": 1448.8646223820033,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "none",
          "repair_status": "repaired",
          "score": 38.40303950625073,
          "uncertainty": 15.58908290969266,
          "unilateral_faults": 0,
          "wins": 14
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 54,
          "capped_draws": 15,
          "coverage_status": "rated",
          "distinct_rated_opponents": 27,
          "draws": 40,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "z-ai/glm-5.2",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-11T17:22:09Z",
          "losses": 11,
          "model": "z-ai/glm-5.2",
          "point_rating_method": "sequential_elo",
          "public_id": "E-40aa28533b1afda1",
          "rated_matches": 54,
          "raw_elo_rating": 1442.1124041249502,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "repaired",
          "score": 36.602494823476015,
          "uncertainty": 23.66998624632421,
          "unilateral_faults": 0,
          "wins": 3
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 56,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 28,
          "draws": 32,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "z-ai/glm-5.2",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 12,
          "model": "z-ai/glm-5.2",
          "point_rating_method": "sequential_elo",
          "public_id": "E-4cab1ccd88bbeb2e",
          "rated_matches": 56,
          "raw_elo_rating": 1484.1155184175784,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 42.45463981090707,
          "uncertainty": 22.47661785325219,
          "unilateral_faults": 0,
          "wins": 12
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 60,
          "capped_draws": 5,
          "coverage_status": "rated",
          "distinct_rated_opponents": 30,
          "draws": 27,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "z-ai/glm-5.2",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-11T14:00:45Z",
          "losses": 21,
          "model": "z-ai/glm-5.2",
          "point_rating_method": "sequential_elo",
          "public_id": "E-583be34ca1fb2631",
          "rated_matches": 60,
          "raw_elo_rating": 1507.6715230136501,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "repaired",
          "score": 45.90433194761855,
          "uncertainty": 20.268439966447993,
          "unilateral_faults": 0,
          "wins": 12
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 124,
          "capped_draws": 8,
          "coverage_status": "rated",
          "distinct_rated_opponents": 43,
          "draws": 30,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "xhigh",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "z-ai/glm-5.2",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_7fad32_to_brackets_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-19T14:50:00Z",
          "losses": 46,
          "model": "z-ai/glm-5.2",
          "point_rating_method": "sequential_elo",
          "public_id": "E-d047860be3ae0d90",
          "rated_matches": 124,
          "raw_elo_rating": 1485.5276957474089,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_7fad32_to_brackets_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "xhigh",
          "repair_status": "first_pass",
          "score": 44.9907509549929,
          "uncertainty": 0.9713595499957961,
          "unilateral_faults": 0,
          "wins": 48
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 120,
          "capped_draws": 10,
          "coverage_status": "rated",
          "distinct_rated_opponents": 43,
          "draws": 50,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "xhigh",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "z-ai/glm-5.2",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_7fad32_to_brackets_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-19T14:50:00Z",
          "losses": 23,
          "model": "z-ai/glm-5.2",
          "point_rating_method": "sequential_elo",
          "public_id": "E-d3a5bd501d8146e0",
          "rated_matches": 120,
          "raw_elo_rating": 1584.6737299429365,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_7fad32_to_brackets_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "xhigh",
          "repair_status": "first_pass",
          "score": 58.417515778425866,
          "uncertainty": 1.7045454545454586,
          "unilateral_faults": 0,
          "wins": 47
        }
      ],
      "GB2-04": [
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 102,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 43,
          "draws": 19,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "xhigh",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-fable-5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-03T17:50:00Z",
          "losses": 5,
          "model": "claude-fable-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-0ca15b39b465b370",
          "rated_matches": 102,
          "raw_elo_rating": 1871.3393976382893,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "xhigh",
          "repair_status": "first_pass",
          "score": 100.0,
          "uncertainty": 5.516463908214657,
          "unilateral_faults": 0,
          "wins": 78
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 80,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 40,
          "draws": 33,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-fable-5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 17,
          "model": "claude-fable-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-eb1f17ce19beffd0",
          "rated_matches": 80,
          "raw_elo_rating": 1582.2001981056562,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 55.133363671974216,
          "uncertainty": 11.805555555555554,
          "unilateral_faults": 0,
          "wins": 30
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 0,
          "capped_draws": 0,
          "coverage_status": "pending",
          "distinct_rated_opponents": 0,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "legacy_shared_thinking_budget",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-opus-4-5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "budget",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 0,
          "model": "claude-opus-4-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-8c9e611d78967342",
          "rated_matches": 0,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "budget",
          "reasoning_setting": "legacy_shared_thinking_budget",
          "repair_status": "first_pass",
          "unilateral_faults": 0,
          "wins": 0
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 78,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 39,
          "draws": 50,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-opus-4-5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "omitted",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 14,
          "model": "claude-opus-4-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-9a77e43e752532c8",
          "rated_matches": 78,
          "raw_elo_rating": 1552.6081087252508,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "omitted",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 50.534733628873596,
          "uncertainty": 12.5043950463012,
          "unilateral_faults": 0,
          "wins": 14
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 104,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 51,
          "draws": 76,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-opus-4-5",
            "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 16,
          "model": "claude-opus-4-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-cbae2963ded72d76",
          "rated_matches": 103,
          "raw_elo_rating": 1477.6181811749257,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 39.978937009585955,
          "uncertainty": 5.279033784546012,
          "unilateral_faults": 0,
          "wins": 11
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 0,
          "capped_draws": 0,
          "coverage_status": "pending",
          "distinct_rated_opponents": 0,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "legacy_shared_thinking_budget",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-opus-4-5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "budget",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 0,
          "model": "claude-opus-4-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-e3449ff084425b16",
          "rated_matches": 0,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "budget",
          "reasoning_setting": "legacy_shared_thinking_budget",
          "repair_status": "first_pass",
          "unilateral_faults": 0,
          "wins": 0
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 159,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 60,
          "draws": 83,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-opus-4-5",
            "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 59,
          "model": "claude-opus-4-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-f40463f635c43598",
          "rated_matches": 159,
          "raw_elo_rating": 1441.887567292159,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "first_pass",
          "score": 35.688547830022806,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 17
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 98,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 42,
          "draws": 37,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "xhigh",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-opus-4-8",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-03T17:20:00Z",
          "losses": 17,
          "model": "claude-opus-4-8",
          "point_rating_method": "sequential_elo",
          "public_id": "E-6344242dae68be1b",
          "rated_matches": 98,
          "raw_elo_rating": 1645.9101696696405,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "xhigh",
          "repair_status": "first_pass",
          "score": 65.49748409048952,
          "uncertainty": 6.501890762960602,
          "unilateral_faults": 0,
          "wins": 44
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 84,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 41,
          "draws": 60,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-opus-4-8",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "omitted",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 15,
          "model": "claude-opus-4-8",
          "point_rating_method": "sequential_elo",
          "public_id": "E-688a139ef8557587",
          "rated_matches": 84,
          "raw_elo_rating": 1480.1348689981835,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "omitted",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 39.727863503836645,
          "uncertainty": 10.482614454664043,
          "unilateral_faults": 0,
          "wins": 9
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 104,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 49,
          "draws": 87,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-opus-4-8",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 12,
          "model": "claude-opus-4-8",
          "point_rating_method": "sequential_elo",
          "public_id": "E-caf91ab5b69b1e64",
          "rated_matches": 104,
          "raw_elo_rating": 1470.653364825019,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 38.94522426719343,
          "uncertainty": 5.045003647426665,
          "unilateral_faults": 0,
          "wins": 5
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 102,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 51,
          "draws": 54,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-opus-5",
            "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-25T15:48:00Z",
          "losses": 31,
          "model": "claude-opus-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-048d3dcf802043b4",
          "rated_matches": 102,
          "raw_elo_rating": 1555.643719772659,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 51.850357271156476,
          "uncertainty": 5.516463908214657,
          "unilateral_faults": 0,
          "wins": 17
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 80,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 34,
          "draws": 11,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "xhigh",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-opus-5",
            "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-25T15:48:00Z",
          "losses": 13,
          "model": "claude-opus-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-4c98514bdb0eaf10",
          "rated_matches": 80,
          "raw_elo_rating": 1701.9517462530455,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "xhigh",
          "repair_status": "first_pass",
          "score": 73.3977703895628,
          "uncertainty": 11.805555555555554,
          "unilateral_faults": 0,
          "wins": 56
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 100,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 50,
          "draws": 56,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-opus-5",
            "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-25T15:48:00Z",
          "losses": 27,
          "model": "claude-opus-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-72e9307528761b35",
          "rated_matches": 100,
          "raw_elo_rating": 1497.2404246856831,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 42.88350947764402,
          "uncertainty": 6.001859510499461,
          "unilateral_faults": 0,
          "wins": 17
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 104,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 52,
          "draws": 28,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-opus-5",
            "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-25T15:48:00Z",
          "losses": 29,
          "model": "claude-opus-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-9e7782014171d35f",
          "rated_matches": 104,
          "raw_elo_rating": 1604.0690744486421,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 59.29367755050637,
          "uncertainty": 5.045003647426665,
          "unilateral_faults": 0,
          "wins": 47
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 84,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 34,
          "draws": 15,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "xhigh",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-opus-5",
            "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-25T15:48:00Z",
          "losses": 6,
          "model": "claude-opus-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-a02883202d334eec",
          "rated_matches": 84,
          "raw_elo_rating": 1837.781141967729,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "xhigh",
          "repair_status": "first_pass",
          "score": 94.27577617470841,
          "uncertainty": 10.482614454664043,
          "unilateral_faults": 0,
          "wins": 63
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 104,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 52,
          "draws": 36,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-opus-5",
            "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-25T15:48:00Z",
          "losses": 26,
          "model": "claude-opus-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-d0f0a2b1c4bbddae",
          "rated_matches": 104,
          "raw_elo_rating": 1562.403382529865,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 52.93886080577703,
          "uncertainty": 5.045003647426665,
          "unilateral_faults": 0,
          "wins": 42
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 76,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 36,
          "draws": 46,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-sonnet-5",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 16,
          "model": "claude-sonnet-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-7031fd4afe7acb91",
          "rated_matches": 76,
          "raw_elo_rating": 1471.7287106223077,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 38.1105048676341,
          "uncertainty": 13.230288229818967,
          "unilateral_faults": 0,
          "wins": 14
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 74,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 36,
          "draws": 40,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "xhigh",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-sonnet-5",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 8,
          "model": "claude-sonnet-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-74d5848169176ddd",
          "rated_matches": 74,
          "raw_elo_rating": 1602.2107727942875,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "xhigh",
          "repair_status": "first_pass",
          "score": 57.919430982158175,
          "uncertainty": 13.985026918962571,
          "unilateral_faults": 0,
          "wins": 26
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 86,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 41,
          "draws": 54,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "xhigh",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-sonnet-5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-03T16:50:00Z",
          "losses": 16,
          "model": "claude-sonnet-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-8e980ad934b3251e",
          "rated_matches": 86,
          "raw_elo_rating": 1534.9415708206361,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "xhigh",
          "repair_status": "first_pass",
          "score": 48.16343828710374,
          "uncertainty": 9.855626741889738,
          "unilateral_faults": 0,
          "wins": 16
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 102,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 49,
          "draws": 72,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-sonnet-5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 11,
          "model": "claude-sonnet-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-b1fc5b99a5deb881",
          "rated_matches": 102,
          "raw_elo_rating": 1482.2172580461772,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "repaired",
          "score": 40.6514142799952,
          "uncertainty": 5.516463908214657,
          "unilateral_faults": 0,
          "wins": 19
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 86,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 43,
          "draws": 69,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-sonnet-5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 7,
          "model": "claude-sonnet-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-be938b7d5557f479",
          "rated_matches": 86,
          "raw_elo_rating": 1509.157122022894,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 44.23081556016269,
          "uncertainty": 9.855626741889738,
          "unilateral_faults": 0,
          "wins": 10
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 74,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 36,
          "draws": 44,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-sonnet-5",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 17,
          "model": "claude-sonnet-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-d4f6be4f3a2580ef",
          "rated_matches": 74,
          "raw_elo_rating": 1490.4637763376538,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 40.87587184385918,
          "uncertainty": 13.985026918962571,
          "unilateral_faults": 0,
          "wins": 13
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 64,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 32,
          "draws": 50,
          "evaluated_setting_identity": {
            "canonical_provider_route": "unknown_legacy",
            "effective_request_value": "enabled",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "cohere/north-mini-code:free",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 11,
          "model": "cohere/north-mini-code",
          "point_rating_method": "sequential_elo",
          "public_id": "E-1460cf3cd86be35c",
          "rated_matches": 64,
          "raw_elo_rating": 1464.2346713769077,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "enabled",
          "repair_status": "repaired",
          "score": 36.352919328591064,
          "uncertainty": 18.26736729460423,
          "unilateral_faults": 0,
          "wins": 3
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 66,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 33,
          "draws": 53,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "deepseek/deepseek-v4-flash",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-01T00:15:48Z",
          "losses": 9,
          "model": "deepseek/deepseek-v4-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-5d143d6301429619",
          "rated_matches": 66,
          "raw_elo_rating": 1470.9778216962018,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 37.49517602497302,
          "uncertainty": 17.33472217815261,
          "unilateral_faults": 0,
          "wins": 4
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 74,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 37,
          "draws": 44,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "deepseek/deepseek-v4-flash",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 26,
          "model": "deepseek/deepseek-v4-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-81bc9a578754f220",
          "rated_matches": 74,
          "raw_elo_rating": 1363.997401760583,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 21.587325373198095,
          "uncertainty": 13.985026918962571,
          "unilateral_faults": 0,
          "wins": 4
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 88,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 44,
          "draws": 54,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "xhigh",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "deepseek/deepseek-v4-pro",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 25,
          "model": "deepseek/deepseek-v4-pro",
          "point_rating_method": "sequential_elo",
          "public_id": "E-38bc194a470fbf62",
          "rated_matches": 88,
          "raw_elo_rating": 1457.4828868208863,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "xhigh",
          "repair_status": "repaired",
          "score": 36.42341278591467,
          "uncertainty": 9.249894000318006,
          "unilateral_faults": 0,
          "wins": 9
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 90,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 41,
          "draws": 64,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "google/gemini-3.1-flash-lite",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 20,
          "model": "google/gemini-3.1-flash-lite",
          "point_rating_method": "sequential_elo",
          "public_id": "E-2be6f5c895691cb3",
          "rated_matches": 90,
          "raw_elo_rating": 1486.643674866353,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "repaired",
          "score": 40.94245051776638,
          "uncertainty": 8.664241836095918,
          "unilateral_faults": 0,
          "wins": 6
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 92,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 43,
          "draws": 77,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "google/gemini-3.1-flash-lite",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 5,
          "model": "google/gemini-3.1-flash-lite",
          "point_rating_method": "sequential_elo",
          "public_id": "E-860c31323fa5eda7",
          "rated_matches": 90,
          "raw_elo_rating": 1494.6174746882057,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "repaired",
          "score": 42.15860784753806,
          "uncertainty": 8.664241836095918,
          "unilateral_faults": 2,
          "wins": 8
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 100,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 48,
          "draws": 57,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "google/gemini-3.5-flash",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 16,
          "model": "google/gemini-3.5-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-32cfa6c9dfb1d16f",
          "rated_matches": 100,
          "raw_elo_rating": 1552.5455372468282,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "repaired",
          "score": 51.31859933665385,
          "uncertainty": 6.001859510499461,
          "unilateral_faults": 0,
          "wins": 27
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 0,
          "capped_draws": 0,
          "coverage_status": "pending",
          "distinct_rated_opponents": 0,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "low",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "google/gemini-3.5-flash",
            "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-21T14:20:15Z",
          "losses": 0,
          "model": "google/gemini-3.5-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-33e6ff93f425b731",
          "rated_matches": 0,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "low",
          "repair_status": "first_pass",
          "unilateral_faults": 0,
          "wins": 0
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 90,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 42,
          "draws": 30,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "google/gemini-3.5-flash",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 38,
          "model": "google/gemini-3.5-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-8e95359e4cbd1851",
          "rated_matches": 90,
          "raw_elo_rating": 1437.4852159713996,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "repaired",
          "score": 33.44484317358223,
          "uncertainty": 8.664241836095918,
          "unilateral_faults": 0,
          "wins": 22
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 137,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 53,
          "draws": 94,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "google/gemini-3.5-flash-lite",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 32,
          "model": "google/gemini-3.5-flash-lite",
          "point_rating_method": "sequential_elo",
          "public_id": "E-39ebef34ae0ea1cb",
          "rated_matches": 136,
          "raw_elo_rating": 1442.4005503966425,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "first_pass",
          "score": 35.37763039440814,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 10
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 114,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 56,
          "draws": 86,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "google/gemini-3.5-flash-lite",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 15,
          "model": "google/gemini-3.5-flash-lite",
          "point_rating_method": "sequential_elo",
          "public_id": "E-5c270e2afa7b70f5",
          "rated_matches": 111,
          "raw_elo_rating": 1487.5247726522077,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 41.70749337777939,
          "uncertainty": 3.4955591261534025,
          "unilateral_faults": 0,
          "wins": 10
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 139,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 55,
          "draws": 109,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "google/gemini-3.5-flash-lite",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 16,
          "model": "google/gemini-3.5-flash-lite",
          "point_rating_method": "sequential_elo",
          "public_id": "E-6098de52ddfabfb1",
          "rated_matches": 133,
          "raw_elo_rating": 1443.188278257529,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 35.439751017064516,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 8
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 134,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 51,
          "draws": 86,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "minimal",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "google/gemini-3.5-flash-lite",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 20,
          "model": "google/gemini-3.5-flash-lite",
          "point_rating_method": "sequential_elo",
          "public_id": "E-6a79049fd9ab6f5d",
          "rated_matches": 128,
          "raw_elo_rating": 1505.2695567320197,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "minimal",
          "repair_status": "first_pass",
          "score": 44.807170228357926,
          "uncertainty": 0.27254531628119416,
          "unilateral_faults": 0,
          "wins": 22
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 136,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 54,
          "draws": 77,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "google/gemini-3.5-flash-lite",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 34,
          "model": "google/gemini-3.5-flash-lite",
          "point_rating_method": "sequential_elo",
          "public_id": "E-953992515ec1424d",
          "rated_matches": 136,
          "raw_elo_rating": 1452.9700185332474,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "first_pass",
          "score": 36.98967690087958,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 25
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 130,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 50,
          "draws": 77,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "minimal",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "google/gemini-3.5-flash-lite",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 25,
          "model": "google/gemini-3.5-flash-lite",
          "point_rating_method": "sequential_elo",
          "public_id": "E-b05b0185d0e8dc2a",
          "rated_matches": 130,
          "raw_elo_rating": 1511.2144902230677,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "minimal",
          "repair_status": "repaired",
          "score": 45.75504750592985,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 28
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 141,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 52,
          "draws": 117,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "minimal",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "google/gemini-3.6-flash",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 14,
          "model": "google/gemini-3.6-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-0b528ba96380a3b5",
          "rated_matches": 141,
          "raw_elo_rating": 1464.6512667915415,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "minimal",
          "repair_status": "first_pass",
          "score": 38.86387825220917,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 10
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 139,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 54,
          "draws": 101,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "minimal",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "google/gemini-3.6-flash",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 26,
          "model": "google/gemini-3.6-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-846809faa1345207",
          "rated_matches": 139,
          "raw_elo_rating": 1477.3695914012185,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "minimal",
          "repair_status": "repaired",
          "score": 40.767227315959126,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 12
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 146,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 55,
          "draws": 38,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "google/gemini-3.6-flash",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 63,
          "model": "google/gemini-3.6-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-a5a73c81dfcf4540",
          "rated_matches": 146,
          "raw_elo_rating": 1481.334460302086,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "first_pass",
          "score": 41.49620719860437,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 45
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 159,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 60,
          "draws": 39,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "google/gemini-3.6-flash",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 27,
          "model": "google/gemini-3.6-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-ccfb6c993d1622b0",
          "rated_matches": 156,
          "raw_elo_rating": 1709.790009047594,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "repaired",
          "score": 76.50294353268006,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 90
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 137,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 55,
          "draws": 102,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "google/gemini-3.6-flash",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 25,
          "model": "google/gemini-3.6-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-cefb1dec9ce36375",
          "rated_matches": 137,
          "raw_elo_rating": 1409.2508299046585,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 30.34058179495447,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 10
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 118,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 59,
          "draws": 86,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "google/gemini-3.6-flash",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 12,
          "model": "google/gemini-3.6-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-d109ab12db58a65f",
          "rated_matches": 118,
          "raw_elo_rating": 1491.0414684830237,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 42.41597592157571,
          "uncertainty": 2.084924851410568,
          "unilateral_faults": 0,
          "wins": 20
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 92,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 40,
          "draws": 75,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "enabled",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "google/gemma-4-31b-it",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 6,
          "model": "google/gemma-4-31b-it",
          "point_rating_method": "sequential_elo",
          "public_id": "E-62ca2464f2212fc9",
          "rated_matches": 90,
          "raw_elo_rating": 1463.0389711785886,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "enabled",
          "repair_status": "repaired",
          "score": 37.342280705591044,
          "uncertainty": 8.664241836095918,
          "unilateral_faults": 2,
          "wins": 9
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 88,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 43,
          "draws": 69,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "google/gemma-4-31b-it",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 9,
          "model": "google/gemma-4-31b-it",
          "point_rating_method": "sequential_elo",
          "public_id": "E-ec0cf4b37c805eee",
          "rated_matches": 88,
          "raw_elo_rating": 1478.369156952384,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 39.60896936866197,
          "uncertainty": 9.249894000318006,
          "unilateral_faults": 0,
          "wins": 10
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 84,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 42,
          "draws": 66,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-4.1",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "omitted",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 14,
          "model": "gpt-4.1",
          "point_rating_method": "sequential_elo",
          "public_id": "E-ecb06954153be8d5",
          "rated_matches": 84,
          "raw_elo_rating": 1457.7387499700872,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "omitted",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 36.31202602070684,
          "uncertainty": 10.482614454664043,
          "unilateral_faults": 0,
          "wins": 4
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 100,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 48,
          "draws": 62,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 21,
          "model": "gpt-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-6f1aae863396df76",
          "rated_matches": 100,
          "raw_elo_rating": 1483.6589592065263,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 40.81207563674785,
          "uncertainty": 6.001859510499461,
          "unilateral_faults": 0,
          "wins": 17
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 94,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 46,
          "draws": 68,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 19,
          "model": "gpt-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-7e3da77777a95e31",
          "rated_matches": 94,
          "raw_elo_rating": 1475.7924746051574,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "repaired",
          "score": 39.423521122325184,
          "uncertainty": 7.54891760425771,
          "unilateral_faults": 0,
          "wins": 7
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 102,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 49,
          "draws": 66,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.4",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 14,
          "model": "gpt-5.4",
          "point_rating_method": "sequential_elo",
          "public_id": "E-0b4132559ee98caf",
          "rated_matches": 102,
          "raw_elo_rating": 1505.7163572188297,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 44.235477379188055,
          "uncertainty": 5.516463908214657,
          "unilateral_faults": 0,
          "wins": 22
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 83,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 37,
          "draws": 42,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.4",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 29,
          "model": "gpt-5.4",
          "point_rating_method": "sequential_elo",
          "public_id": "E-5cd71ee548acca75",
          "rated_matches": 83,
          "raw_elo_rating": 1417.712515509699,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 30.16798634189743,
          "uncertainty": 10.804472558998102,
          "unilateral_faults": 0,
          "wins": 12
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 90,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 44,
          "draws": 71,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.4",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 8,
          "model": "gpt-5.4",
          "point_rating_method": "sequential_elo",
          "public_id": "E-8d62bf1b340a70dc",
          "rated_matches": 90,
          "raw_elo_rating": 1483.8733493227608,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 40.51992276550704,
          "uncertainty": 8.664241836095918,
          "unilateral_faults": 0,
          "wins": 11
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 85,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 37,
          "draws": 43,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "xhigh",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.4",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 4,
          "model": "gpt-5.4",
          "point_rating_method": "sequential_elo",
          "public_id": "E-8d6c86dd58efc4be",
          "rated_matches": 82,
          "raw_elo_rating": 1602.7644735229496,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "xhigh",
          "repair_status": "first_pass",
          "score": 58.3519781342059,
          "uncertainty": 11.132129994845172,
          "unilateral_faults": 0,
          "wins": 35
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 96,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 43,
          "draws": 36,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "xhigh",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.4",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 24,
          "model": "gpt-5.4",
          "point_rating_method": "sequential_elo",
          "public_id": "E-9279285adff8ed29",
          "rated_matches": 96,
          "raw_elo_rating": 1637.1951751819909,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "xhigh",
          "repair_status": "first_pass",
          "score": 64.10539152692174,
          "uncertainty": 7.017308256680951,
          "unilateral_faults": 0,
          "wins": 36
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 82,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 37,
          "draws": 41,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.4",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 33,
          "model": "gpt-5.4",
          "point_rating_method": "sequential_elo",
          "public_id": "E-cae96a5e03c2613e",
          "rated_matches": 82,
          "raw_elo_rating": 1395.4317548321806,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 26.729763986537332,
          "uncertainty": 11.132129994845172,
          "unilateral_faults": 0,
          "wins": 8
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 90,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 44,
          "draws": 58,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.4-mini",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 16,
          "model": "gpt-5.4-mini",
          "point_rating_method": "sequential_elo",
          "public_id": "E-0880cdf1a43cb90c",
          "rated_matches": 90,
          "raw_elo_rating": 1460.0297776195794,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 36.883321001904825,
          "uncertainty": 8.664241836095918,
          "unilateral_faults": 0,
          "wins": 16
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 90,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 45,
          "draws": 61,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.4-mini",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 9,
          "model": "gpt-5.4-mini",
          "point_rating_method": "sequential_elo",
          "public_id": "E-74f5bcc8ad3796a5",
          "rated_matches": 90,
          "raw_elo_rating": 1559.7577793037303,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 52.09375303448146,
          "uncertainty": 8.664241836095918,
          "unilateral_faults": 0,
          "wins": 20
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 98,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 46,
          "draws": 64,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.4-nano",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-09T17:30:50Z",
          "losses": 9,
          "model": "gpt-5.4-nano",
          "point_rating_method": "sequential_elo",
          "public_id": "E-a32cb67d48c62b3b",
          "rated_matches": 98,
          "raw_elo_rating": 1562.2888242629197,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "repaired",
          "score": 52.743625903198904,
          "uncertainty": 6.501890762960602,
          "unilateral_faults": 0,
          "wins": 25
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 86,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 42,
          "draws": 45,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "xhigh",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 35,
          "model": "gpt-5.5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-64bf5daf186f8119",
          "rated_matches": 86,
          "raw_elo_rating": 1398.6125264834243,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "xhigh",
          "repair_status": "first_pass",
          "score": 27.370645611635616,
          "uncertainty": 9.855626741889738,
          "unilateral_faults": 0,
          "wins": 6
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 102,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 51,
          "draws": 63,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 17,
          "model": "gpt-5.5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-9e7bdad81107b7e4",
          "rated_matches": 102,
          "raw_elo_rating": 1475.5304118625747,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 39.63154205082826,
          "uncertainty": 5.516463908214657,
          "unilateral_faults": 0,
          "wins": 22
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 96,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 47,
          "draws": 66,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 18,
          "model": "gpt-5.5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-ba1aa87056709e9a",
          "rated_matches": 96,
          "raw_elo_rating": 1487.1646241939861,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 41.222856430705775,
          "uncertainty": 7.017308256680951,
          "unilateral_faults": 0,
          "wins": 12
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 78,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 36,
          "draws": 44,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "xhigh",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.6-luna",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 23,
          "model": "gpt-5.6-luna",
          "point_rating_method": "sequential_elo",
          "public_id": "E-0a9286b0c21ae9be",
          "rated_matches": 78,
          "raw_elo_rating": 1418.4061831629094,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "xhigh",
          "repair_status": "first_pass",
          "score": 30.06636734322581,
          "uncertainty": 12.5043950463012,
          "unilateral_faults": 0,
          "wins": 11
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 78,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 38,
          "draws": 52,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.6-luna",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 15,
          "model": "gpt-5.6-luna",
          "point_rating_method": "sequential_elo",
          "public_id": "E-2c7615f28028f790",
          "rated_matches": 78,
          "raw_elo_rating": 1460.346288772209,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 36.463037436242594,
          "uncertainty": 12.5043950463012,
          "unilateral_faults": 0,
          "wins": 11
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 78,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 36,
          "draws": 58,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.6-luna",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 11,
          "model": "gpt-5.6-luna",
          "point_rating_method": "sequential_elo",
          "public_id": "E-3c11110e415436c3",
          "rated_matches": 78,
          "raw_elo_rating": 1445.8487821616854,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 34.25188976239682,
          "uncertainty": 12.5043950463012,
          "unilateral_faults": 0,
          "wins": 9
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 98,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 47,
          "draws": 87,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.6-luna",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-10T05:30:29Z",
          "losses": 5,
          "model": "gpt-5.6-luna",
          "point_rating_method": "sequential_elo",
          "public_id": "E-5389e160269f5ceb",
          "rated_matches": 98,
          "raw_elo_rating": 1494.8994434966728,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 42.465453488707176,
          "uncertainty": 6.501890762960602,
          "unilateral_faults": 0,
          "wins": 6
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 88,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 43,
          "draws": 68,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.6-luna",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-10T05:30:29Z",
          "losses": 13,
          "model": "gpt-5.6-luna",
          "point_rating_method": "sequential_elo",
          "public_id": "E-71a01107bf3f9fc1",
          "rated_matches": 88,
          "raw_elo_rating": 1475.7905244904262,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 39.21567848608893,
          "uncertainty": 9.249894000318006,
          "unilateral_faults": 0,
          "wins": 7
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 86,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 42,
          "draws": 44,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "xhigh",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.6-luna",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-10T05:30:29Z",
          "losses": 25,
          "model": "gpt-5.6-luna",
          "point_rating_method": "sequential_elo",
          "public_id": "E-e348813cda8b38b7",
          "rated_matches": 86,
          "raw_elo_rating": 1491.9345388012882,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "xhigh",
          "repair_status": "first_pass",
          "score": 41.6040414636828,
          "uncertainty": 9.855626741889738,
          "unilateral_faults": 0,
          "wins": 17
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 98,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 44,
          "draws": 44,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "xhigh",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.6-sol",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-10T05:30:29Z",
          "losses": 6,
          "model": "gpt-5.6-sol",
          "point_rating_method": "sequential_elo",
          "public_id": "E-270a233119b6cc62",
          "rated_matches": 98,
          "raw_elo_rating": 1661.9721859570288,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "xhigh",
          "repair_status": "first_pass",
          "score": 67.94724948155005,
          "uncertainty": 6.501890762960602,
          "unilateral_faults": 0,
          "wins": 48
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 82,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 37,
          "draws": 54,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.6-sol",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 15,
          "model": "gpt-5.6-sol",
          "point_rating_method": "sequential_elo",
          "public_id": "E-66db807b1be40f67",
          "rated_matches": 82,
          "raw_elo_rating": 1494.2951959311706,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 41.80833395633762,
          "uncertainty": 11.132129994845172,
          "unilateral_faults": 0,
          "wins": 13
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 78,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 36,
          "draws": 8,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "xhigh",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.6-sol",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 2,
          "model": "gpt-5.6-sol",
          "point_rating_method": "sequential_elo",
          "public_id": "E-6b542c5d0dcf2279",
          "rated_matches": 78,
          "raw_elo_rating": 1810.5520082026756,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "xhigh",
          "repair_status": "first_pass",
          "score": 89.87612305774321,
          "uncertainty": 12.5043950463012,
          "unilateral_faults": 0,
          "wins": 68
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 78,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 36,
          "draws": 11,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.6-sol",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 3,
          "model": "gpt-5.6-sol",
          "point_rating_method": "sequential_elo",
          "public_id": "E-7f8aa62c2a56b424",
          "rated_matches": 78,
          "raw_elo_rating": 1802.997606042514,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 88.72393191119036,
          "uncertainty": 12.5043950463012,
          "unilateral_faults": 0,
          "wins": 64
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 108,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 52,
          "draws": 86,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.6-sol",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-10T05:30:29Z",
          "losses": 6,
          "model": "gpt-5.6-sol",
          "point_rating_method": "sequential_elo",
          "public_id": "E-c81bf4d15f3d48f1",
          "rated_matches": 108,
          "raw_elo_rating": 1524.9887263647072,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 47.3426724694463,
          "uncertainty": 4.1413142610575715,
          "unilateral_faults": 0,
          "wins": 16
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 82,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 41,
          "draws": 63,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.6-sol",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-10T10:07:13Z",
          "losses": 6,
          "model": "gpt-5.6-sol",
          "point_rating_method": "sequential_elo",
          "public_id": "E-f0b7195272d6417e",
          "rated_matches": 82,
          "raw_elo_rating": 1498.3796453332363,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 42.431290788636126,
          "uncertainty": 11.132129994845172,
          "unilateral_faults": 0,
          "wins": 13
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 90,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 45,
          "draws": 76,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.6-terra",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-10T05:30:29Z",
          "losses": 6,
          "model": "gpt-5.6-terra",
          "point_rating_method": "sequential_elo",
          "public_id": "E-50ee0aadbc66fe0e",
          "rated_matches": 90,
          "raw_elo_rating": 1521.160171149716,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 46.206877878735085,
          "uncertainty": 8.664241836095918,
          "unilateral_faults": 0,
          "wins": 8
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 98,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 48,
          "draws": 76,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.6-terra",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-10T05:30:29Z",
          "losses": 9,
          "model": "gpt-5.6-terra",
          "point_rating_method": "sequential_elo",
          "public_id": "E-89c18d144e85d89f",
          "rated_matches": 98,
          "raw_elo_rating": 1510.6341572765252,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 44.865298973012386,
          "uncertainty": 6.501890762960602,
          "unilateral_faults": 0,
          "wins": 13
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 94,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 44,
          "draws": 44,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "xhigh",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.6-terra",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-10T05:30:29Z",
          "losses": 18,
          "model": "gpt-5.6-terra",
          "point_rating_method": "sequential_elo",
          "public_id": "E-b85c80e7475ef9ec",
          "rated_matches": 94,
          "raw_elo_rating": 1568.1292217619282,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "xhigh",
          "repair_status": "first_pass",
          "score": 53.506645149871794,
          "uncertainty": 7.54891760425771,
          "unilateral_faults": 0,
          "wins": 32
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 50,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 25,
          "draws": 36,
          "evaluated_setting_identity": {
            "canonical_provider_route": "unknown_legacy",
            "effective_request_value": "enabled",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "inclusionai/ling-3.0-flash:free",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 10,
          "model": "inclusionai/ling-3.0-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-20e94e7276184071",
          "rated_matches": 50,
          "raw_elo_rating": 1425.6994207944547,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "enabled",
          "repair_status": "repaired",
          "score": 29.499842559488023,
          "uncertainty": 26.264004201400486,
          "unilateral_faults": 0,
          "wins": 4
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 116,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 45,
          "draws": 102,
          "evaluated_setting_identity": {
            "canonical_provider_route": "unknown_legacy",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "inclusionai/ling-3.0-flash:free",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 7,
          "model": "inclusionai/ling-3.0-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-f38039bb8cc277a1",
          "rated_matches": 116,
          "raw_elo_rating": 1476.192389292363,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 40.10360954415184,
          "uncertainty": 2.4750163521024238,
          "unilateral_faults": 0,
          "wins": 7
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 143,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 51,
          "draws": 60,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "enabled",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "meituan/longcat-2.0",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 46,
          "model": "meituan/longcat-2.0",
          "point_rating_method": "sequential_elo",
          "public_id": "E-4ccf296e55b59be3",
          "rated_matches": 120,
          "raw_elo_rating": 1321.5639506069945,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "enabled",
          "repair_status": "repaired",
          "score": 16.613817698425585,
          "uncertainty": 1.7045454545454586,
          "unilateral_faults": 23,
          "wins": 14
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 142,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 55,
          "draws": 93,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "enabled",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "meituan/longcat-2.0",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 44,
          "model": "meituan/longcat-2.0",
          "point_rating_method": "sequential_elo",
          "public_id": "E-9c9e87bb30b3cb99",
          "rated_matches": 142,
          "raw_elo_rating": 1352.2288317182251,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "enabled",
          "repair_status": "first_pass",
          "score": 21.735234055222836,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 5
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 102,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 51,
          "draws": 56,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "meituan/longcat-2.0",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 24,
          "model": "meituan/longcat-2.0",
          "point_rating_method": "sequential_elo",
          "public_id": "E-9e1d4bf411e97fa6",
          "rated_matches": 102,
          "raw_elo_rating": 1584.2614626043232,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 56.21511165223179,
          "uncertainty": 5.516463908214657,
          "unilateral_faults": 0,
          "wins": 22
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 76,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 36,
          "draws": 54,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "minimal",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "meta/muse-spark-1.2",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-08-13T16:58:34Z",
          "losses": 9,
          "model": "meta/muse-spark-1.2",
          "point_rating_method": "sequential_elo",
          "public_id": "E-3f1d300b580e2822",
          "rated_matches": 76,
          "raw_elo_rating": 1482.7694515360909,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "minimal",
          "repair_status": "first_pass",
          "score": 39.7944295068769,
          "uncertainty": 13.230288229818967,
          "unilateral_faults": 0,
          "wins": 13
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 76,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 36,
          "draws": 40,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "meta/muse-spark-1.2",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-08-13T16:58:34Z",
          "losses": 27,
          "model": "meta/muse-spark-1.2",
          "point_rating_method": "sequential_elo",
          "public_id": "E-57e6f935250459a2",
          "rated_matches": 76,
          "raw_elo_rating": 1411.1381799035316,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 28.86928741865205,
          "uncertainty": 13.230288229818967,
          "unilateral_faults": 0,
          "wins": 9
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 92,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 44,
          "draws": 76,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "enabled",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "minimax/minimax-m3",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 9,
          "model": "minimax/minimax-m3",
          "point_rating_method": "sequential_elo",
          "public_id": "E-c60620c3c72a6064",
          "rated_matches": 92,
          "raw_elo_rating": 1483.269501274785,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "enabled",
          "repair_status": "repaired",
          "score": 40.496965218840195,
          "uncertainty": 8.09758473652126,
          "unilateral_faults": 0,
          "wins": 7
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 102,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 49,
          "draws": 79,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "enabled",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "moonshotai/kimi-k2.7-code",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 15,
          "model": "moonshotai/kimi-k2.7-code",
          "point_rating_method": "sequential_elo",
          "public_id": "E-eb97811a38950c20",
          "rated_matches": 102,
          "raw_elo_rating": 1431.1215027312614,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "enabled",
          "repair_status": "repaired",
          "score": 32.85833209398961,
          "uncertainty": 5.516463908214657,
          "unilateral_faults": 0,
          "wins": 8
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 156,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 63,
          "draws": 81,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "low",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "moonshotai/kimi-k3",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T14:00:00Z",
          "losses": 31,
          "model": "moonshotai/kimi-k3",
          "point_rating_method": "sequential_elo",
          "public_id": "E-3c06949f23d4a77f",
          "rated_matches": 156,
          "raw_elo_rating": 1514.343293683398,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "low",
          "repair_status": "repaired",
          "score": 46.69357274580004,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 44
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 152,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 58,
          "draws": 47,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "max",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "moonshotai/kimi-k3",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T14:00:00Z",
          "losses": 19,
          "model": "moonshotai/kimi-k3",
          "point_rating_method": "sequential_elo",
          "public_id": "E-601725df2c678708",
          "rated_matches": 152,
          "raw_elo_rating": 1735.222095654677,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "max",
          "repair_status": "repaired",
          "score": 80.31858860898552,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 86
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 137,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 53,
          "draws": 94,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "moonshotai/kimi-k3",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T14:00:00Z",
          "losses": 17,
          "model": "moonshotai/kimi-k3",
          "point_rating_method": "sequential_elo",
          "public_id": "E-7c724729d138057b",
          "rated_matches": 133,
          "raw_elo_rating": 1483.9182974099629,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "first_pass",
          "score": 41.65185972817385,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 22
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 96,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 47,
          "draws": 83,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "nex-agi/nex-n2-pro",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-11T17:22:09Z",
          "losses": 8,
          "model": "nex-agi/nex-n2-pro",
          "point_rating_method": "sequential_elo",
          "public_id": "E-6f4b3b55e4ec7cf5",
          "rated_matches": 96,
          "raw_elo_rating": 1464.340110846728,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "none",
          "repair_status": "repaired",
          "score": 37.74168060162787,
          "uncertainty": 7.017308256680951,
          "unilateral_faults": 0,
          "wins": 5
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 90,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 44,
          "draws": 65,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "nvidia/nemotron-3-ultra-550b-a55b",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-11T17:22:09Z",
          "losses": 19,
          "model": "nvidia/nemotron-3-ultra-550b-a55b",
          "point_rating_method": "sequential_elo",
          "public_id": "E-958dea26b779a042",
          "rated_matches": 90,
          "raw_elo_rating": 1461.9284785190819,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "repaired",
          "score": 37.17290928698389,
          "uncertainty": 8.664241836095918,
          "unilateral_faults": 0,
          "wins": 6
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 62,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 31,
          "draws": 48,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "nvidia/nemotron-3-ultra-550b-a55b",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 7,
          "model": "nvidia/nemotron-3-ultra-550b-a55b",
          "point_rating_method": "sequential_elo",
          "public_id": "E-f36b99b3d76fbb35",
          "rated_matches": 62,
          "raw_elo_rating": 1498.4721260722356,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 41.455613711503254,
          "uncertainty": 19.244078834871203,
          "unilateral_faults": 0,
          "wins": 7
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 88,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 42,
          "draws": 67,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "o3",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 12,
          "model": "o3",
          "point_rating_method": "sequential_elo",
          "public_id": "E-7e92e17a121661f4",
          "rated_matches": 88,
          "raw_elo_rating": 1452.4224780953568,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 35.65160344774605,
          "uncertainty": 9.249894000318006,
          "unilateral_faults": 0,
          "wins": 9
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 80,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 39,
          "draws": 43,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "openai/gpt-oss-120b",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 23,
          "model": "openai/gpt-oss-120b",
          "point_rating_method": "sequential_elo",
          "public_id": "E-3a27113d21c73b01",
          "rated_matches": 80,
          "raw_elo_rating": 1479.2518107556666,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "repaired",
          "score": 39.431761090888465,
          "uncertainty": 11.805555555555554,
          "unilateral_faults": 0,
          "wins": 14
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 96,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 46,
          "draws": 83,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "openai/gpt-oss-120b",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 11,
          "model": "openai/gpt-oss-120b",
          "point_rating_method": "sequential_elo",
          "public_id": "E-f1288f2abfdbbfe4",
          "rated_matches": 96,
          "raw_elo_rating": 1452.7004190221962,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "repaired",
          "score": 35.96640446666731,
          "uncertainty": 7.017308256680951,
          "unilateral_faults": 0,
          "wins": 2
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 132,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 52,
          "draws": 52,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "low",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "openai/gpt-oss-120b",
            "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-21T14:20:15Z",
          "losses": 71,
          "model": "openai/gpt-oss-120b",
          "point_rating_method": "sequential_elo",
          "public_id": "E-f6de1ce39e48807c",
          "rated_matches": 132,
          "raw_elo_rating": 1210.9553390354572,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "low",
          "repair_status": "repaired",
          "score": 0.0,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 9
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 152,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 59,
          "draws": 94,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "enabled",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "poolside/laguna-s-2.1",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 46,
          "model": "poolside/laguna-s-2.1",
          "point_rating_method": "sequential_elo",
          "public_id": "E-e996fd38983e3b7f",
          "rated_matches": 152,
          "raw_elo_rating": 1380.6694525948496,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "enabled",
          "repair_status": "repaired",
          "score": 26.24251380391939,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 12
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 106,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 47,
          "draws": 66,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "enabled",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "qwen/qwen3.7-max",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 23,
          "model": "qwen/qwen3.7-max",
          "point_rating_method": "sequential_elo",
          "public_id": "E-ea08328e287de1ad",
          "rated_matches": 106,
          "raw_elo_rating": 1490.791657928284,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "enabled",
          "repair_status": "first_pass",
          "score": 42.07260490289768,
          "uncertainty": 4.586824452283178,
          "unilateral_faults": 0,
          "wins": 17
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 74,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 36,
          "draws": 61,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "qwen/qwen3.7-plus",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 8,
          "model": "qwen/qwen3.7-plus",
          "point_rating_method": "sequential_elo",
          "public_id": "E-84b9a07f75f324e2",
          "rated_matches": 74,
          "raw_elo_rating": 1469.91418843072,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 37.7416657545222,
          "uncertainty": 13.985026918962571,
          "unilateral_faults": 0,
          "wins": 5
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 16,
          "capped_draws": 0,
          "coverage_status": "under_covered",
          "distinct_rated_opponents": 8,
          "draws": 9,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "qwen/qwen3.8-max",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 4,
          "model": "qwen/qwen3.8-max",
          "point_rating_method": "sequential_elo",
          "public_id": "E-1f87c69eddf28f4e",
          "rated_matches": 16,
          "raw_elo_rating": 1475.637623633983,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 30.86262516391439,
          "uncertainty": 77.5178125181665,
          "unilateral_faults": 0,
          "wins": 3
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 20,
          "capped_draws": 0,
          "coverage_status": "under_covered",
          "distinct_rated_opponents": 11,
          "draws": 10,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "xhigh",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "qwen/qwen3.8-max",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-08-18T17:01:47Z",
          "losses": 1,
          "model": "qwen/qwen3.8-max",
          "point_rating_method": "sequential_elo",
          "public_id": "E-2c5709bd26aef5e5",
          "rated_matches": 20,
          "raw_elo_rating": 1594.1909851365033,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "xhigh",
          "repair_status": "first_pass",
          "score": 50.427853739274326,
          "uncertainty": 65.3589451179962,
          "unilateral_faults": 0,
          "wins": 9
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 22,
          "capped_draws": 0,
          "coverage_status": "under_covered",
          "distinct_rated_opponents": 11,
          "draws": 17,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "minimal",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "qwen/qwen3.8-max",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 4,
          "model": "qwen/qwen3.8-max",
          "point_rating_method": "sequential_elo",
          "public_id": "E-91e0eadd75202409",
          "rated_matches": 22,
          "raw_elo_rating": 1458.4779270736012,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "minimal",
          "repair_status": "first_pass",
          "score": 30.32099723181149,
          "uncertainty": 60.5072070285374,
          "unilateral_faults": 0,
          "wins": 1
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 16,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 8,
          "draws": 11,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "low",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "stealth/ox-alpha",
            "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-08-22T00:27:26Z",
          "losses": 5,
          "model": "stealth/ox-alpha",
          "point_rating_method": "sequential_elo",
          "public_id": "E-2aaa1a2095c3d9b6",
          "rated_matches": 16,
          "raw_elo_rating": 1445.1248130404315,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "low",
          "repair_status": "first_pass",
          "score": 26.208836620893216,
          "uncertainty": 77.5178125181665,
          "unilateral_faults": 0,
          "wins": 0
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 16,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 8,
          "draws": 8,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "stealth/ox-alpha",
            "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-08-22T00:27:26Z",
          "losses": 2,
          "model": "stealth/ox-alpha",
          "point_rating_method": "sequential_elo",
          "public_id": "E-43ae1b9ca4bd7996",
          "rated_matches": 16,
          "raw_elo_rating": 1544.9767970254613,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "repaired",
          "score": 41.43817833108209,
          "uncertainty": 77.5178125181665,
          "unilateral_faults": 0,
          "wins": 6
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 16,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 8,
          "draws": 2,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "max",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "stealth/ox-alpha",
            "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-08-22T00:27:26Z",
          "losses": 0,
          "model": "stealth/ox-alpha",
          "point_rating_method": "sequential_elo",
          "public_id": "E-454f79b70ee12fe0",
          "rated_matches": 16,
          "raw_elo_rating": 1660.6322344500543,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "max",
          "repair_status": "first_pass",
          "score": 59.07784964141441,
          "uncertainty": 77.5178125181665,
          "unilateral_faults": 0,
          "wins": 14
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 16,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 8,
          "draws": 11,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "stealth/ox-alpha",
            "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-08-22T00:27:26Z",
          "losses": 3,
          "model": "stealth/ox-alpha",
          "point_rating_method": "sequential_elo",
          "public_id": "E-6139f660620fd73b",
          "rated_matches": 16,
          "raw_elo_rating": 1499.2139224856492,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "first_pass",
          "score": 34.45846269406692,
          "uncertainty": 77.5178125181665,
          "unilateral_faults": 0,
          "wins": 2
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 16,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 8,
          "draws": 7,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "max",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "stealth/ox-alpha",
            "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-08-22T00:27:26Z",
          "losses": 5,
          "model": "stealth/ox-alpha",
          "point_rating_method": "sequential_elo",
          "public_id": "E-6a2b79a57d322dae",
          "rated_matches": 16,
          "raw_elo_rating": 1484.413760171134,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "max",
          "repair_status": "first_pass",
          "score": 32.20115422348307,
          "uncertainty": 77.5178125181665,
          "unilateral_faults": 0,
          "wins": 4
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 16,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 8,
          "draws": 8,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "low",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "stealth/ox-alpha",
            "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-08-22T00:27:26Z",
          "losses": 7,
          "model": "stealth/ox-alpha",
          "point_rating_method": "sequential_elo",
          "public_id": "E-92dc825a33843ff8",
          "rated_matches": 16,
          "raw_elo_rating": 1430.6077613290613,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "low",
          "repair_status": "repaired",
          "score": 23.994707944490706,
          "uncertainty": 77.5178125181665,
          "unilateral_faults": 0,
          "wins": 1
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 16,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 8,
          "draws": 10,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "low",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "stealth/ox-alpha",
            "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-08-22T00:27:26Z",
          "losses": 4,
          "model": "stealth/ox-alpha",
          "point_rating_method": "sequential_elo",
          "public_id": "E-ac806e30e1bd1958",
          "rated_matches": 16,
          "raw_elo_rating": 1473.4725162866634,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "low",
          "repair_status": "repaired",
          "score": 30.532404788558484,
          "uncertainty": 77.5178125181665,
          "unilateral_faults": 0,
          "wins": 2
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 16,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 8,
          "draws": 11,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "stealth/ox-alpha",
            "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-08-22T00:27:26Z",
          "losses": 4,
          "model": "stealth/ox-alpha",
          "point_rating_method": "sequential_elo",
          "public_id": "E-be47453e36658247",
          "rated_matches": 16,
          "raw_elo_rating": 1465.4137098841509,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "first_pass",
          "score": 29.30328232566859,
          "uncertainty": 77.5178125181665,
          "unilateral_faults": 0,
          "wins": 1
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 16,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 8,
          "draws": 8,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "max",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "stealth/ox-alpha",
            "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-08-22T00:27:26Z",
          "losses": 4,
          "model": "stealth/ox-alpha",
          "point_rating_method": "sequential_elo",
          "public_id": "E-d89754cdf98b2ae2",
          "rated_matches": 16,
          "raw_elo_rating": 1496.1444853273942,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "max",
          "repair_status": "first_pass",
          "score": 33.990314686632,
          "uncertainty": 77.5178125181665,
          "unilateral_faults": 0,
          "wins": 4
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 98,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 47,
          "draws": 76,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "stepfun/step-3.7-flash",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 11,
          "model": "stepfun/step-3.7-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-25e56c6bfae33c62",
          "rated_matches": 98,
          "raw_elo_rating": 1518.32655258939,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "repaired",
          "score": 46.03853672066733,
          "uncertainty": 6.501890762960602,
          "unilateral_faults": 0,
          "wins": 11
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 72,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 36,
          "draws": 44,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "tencent/hy3-preview",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 13,
          "model": "tencent/hy3-preview",
          "point_rating_method": "sequential_elo",
          "public_id": "E-3fd10f7865cc280e",
          "rated_matches": 72,
          "raw_elo_rating": 1506.6569734340017,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "repaired",
          "score": 43.249796081077825,
          "uncertainty": 14.770573598065289,
          "unilateral_faults": 0,
          "wins": 15
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 86,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 42,
          "draws": 60,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "tencent/hy3-preview",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 19,
          "model": "tencent/hy3-preview",
          "point_rating_method": "sequential_elo",
          "public_id": "E-51c104b34ef2a244",
          "rated_matches": 86,
          "raw_elo_rating": 1428.305372108474,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "first_pass",
          "score": 31.89937377831447,
          "uncertainty": 9.855626741889738,
          "unilateral_faults": 0,
          "wins": 7
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 86,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 42,
          "draws": 47,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "thinkingmachines/inkling",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 21,
          "model": "thinkingmachines/inkling",
          "point_rating_method": "sequential_elo",
          "public_id": "E-646ff33c7bab8b13",
          "rated_matches": 86,
          "raw_elo_rating": 1423.5390952609764,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 31.17242519002416,
          "uncertainty": 9.855626741889738,
          "unilateral_faults": 0,
          "wins": 18
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 92,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 45,
          "draws": 77,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "thinkingmachines/inkling",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 11,
          "model": "thinkingmachines/inkling",
          "point_rating_method": "sequential_elo",
          "public_id": "E-ddc16fa197bfc7c5",
          "rated_matches": 92,
          "raw_elo_rating": 1481.1560146919048,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 40.174617999626136,
          "uncertainty": 8.09758473652126,
          "unilateral_faults": 0,
          "wins": 4
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 134,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 53,
          "draws": 84,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "max",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "thinkingmachines/inkling",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 22,
          "model": "thinkingmachines/inkling",
          "point_rating_method": "sequential_elo",
          "public_id": "E-f130161523da1e6b",
          "rated_matches": 134,
          "raw_elo_rating": 1476.2686847664681,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "max",
          "repair_status": "first_pass",
          "score": 40.504702920191605,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 28
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 120,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 46,
          "draws": 94,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "thinkingmachines/inkling",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 19,
          "model": "thinkingmachines/inkling",
          "point_rating_method": "sequential_elo",
          "public_id": "E-fce01db31ecf26d2",
          "rated_matches": 120,
          "raw_elo_rating": 1454.3921381611772,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 36.872662603409985,
          "uncertainty": 1.7045454545454586,
          "unilateral_faults": 0,
          "wins": 7
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 20,
          "capped_draws": 0,
          "coverage_status": "under_covered",
          "distinct_rated_opponents": 10,
          "draws": 13,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "thinkingmachines/inkling-small",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 5,
          "model": "thinkingmachines/inkling-small",
          "point_rating_method": "sequential_elo",
          "public_id": "E-20d371c6aae692a2",
          "rated_matches": 20,
          "raw_elo_rating": 1469.3700914144779,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "repaired",
          "score": 31.39027464270986,
          "uncertainty": 65.3589451179962,
          "unilateral_faults": 0,
          "wins": 2
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 15,
          "capped_draws": 0,
          "coverage_status": "under_covered",
          "distinct_rated_opponents": 8,
          "draws": 13,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "thinkingmachines/inkling-small",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 0,
          "model": "thinkingmachines/inkling-small",
          "point_rating_method": "sequential_elo",
          "public_id": "E-a50e6392704c24e8",
          "rated_matches": 15,
          "raw_elo_rating": 1525.0357629986581,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 37.941404265071526,
          "uncertainty": 81.25,
          "unilateral_faults": 0,
          "wins": 2
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 17,
          "capped_draws": 0,
          "coverage_status": "under_covered",
          "distinct_rated_opponents": 8,
          "draws": 9,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "max",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "thinkingmachines/inkling-small",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-08-18T19:36:24Z",
          "losses": 1,
          "model": "thinkingmachines/inkling-small",
          "point_rating_method": "sequential_elo",
          "public_id": "E-df6d76539ff35338",
          "rated_matches": 17,
          "raw_elo_rating": 1562.2633173996858,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "max",
          "repair_status": "repaired",
          "score": 44.49159171005959,
          "uncertainty": 74.10113019775793,
          "unilateral_faults": 0,
          "wins": 7
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 154,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 59,
          "draws": 64,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "x-ai/grok-4.5",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T14:00:00Z",
          "losses": 54,
          "model": "x-ai/grok-4.5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-07caaa12175b0b3c",
          "rated_matches": 154,
          "raw_elo_rating": 1419.3352985192469,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "first_pass",
          "score": 32.171720342982304,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 36
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 133,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 51,
          "draws": 96,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "low",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "x-ai/grok-4.5",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T14:00:00Z",
          "losses": 21,
          "model": "x-ai/grok-4.5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-5a4033db1131bf1d",
          "rated_matches": 133,
          "raw_elo_rating": 1428.310826299396,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "low",
          "repair_status": "first_pass",
          "score": 33.17065439419427,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 16
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 110,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 54,
          "draws": 82,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "x-ai/grok-4.5",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T14:00:00Z",
          "losses": 16,
          "model": "x-ai/grok-4.5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-ba6a8e6d7fc9a48d",
          "rated_matches": 110,
          "raw_elo_rating": 1479.3694583369315,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 40.43774279100727,
          "uncertainty": 3.707899787624953,
          "unilateral_faults": 0,
          "wins": 12
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 96,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 46,
          "draws": 84,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "enabled",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "x-ai/grok-build-0.1",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 7,
          "model": "x-ai/grok-build-0.1",
          "point_rating_method": "sequential_elo",
          "public_id": "E-85934b32572399da",
          "rated_matches": 96,
          "raw_elo_rating": 1480.7467967975713,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "enabled",
          "repair_status": "repaired",
          "score": 40.244014723647986,
          "uncertainty": 7.017308256680951,
          "unilateral_faults": 0,
          "wins": 5
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 90,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 42,
          "draws": 64,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "xiaomi/mimo-v2.5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T06:10:40Z",
          "losses": 19,
          "model": "xiaomi/mimo-v2.5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-00e6914e513b1656",
          "rated_matches": 90,
          "raw_elo_rating": 1465.9648732385099,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "repaired",
          "score": 37.78853685897672,
          "uncertainty": 8.664241836095918,
          "unilateral_faults": 0,
          "wins": 7
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 96,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 45,
          "draws": 65,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "xiaomi/mimo-v2.5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-01T00:15:48Z",
          "losses": 26,
          "model": "xiaomi/mimo-v2.5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-23e877112cb95491",
          "rated_matches": 96,
          "raw_elo_rating": 1454.1533586667938,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "repaired",
          "score": 36.18800561517503,
          "uncertainty": 7.017308256680951,
          "unilateral_faults": 0,
          "wins": 5
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 106,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 47,
          "draws": 90,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "enabled",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "xiaomi/mimo-v2.5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 12,
          "model": "xiaomi/mimo-v2.5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-2f7e15b8aa123825",
          "rated_matches": 106,
          "raw_elo_rating": 1474.3257249175822,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "enabled",
          "repair_status": "repaired",
          "score": 39.56123446848897,
          "uncertainty": 4.586824452283178,
          "unilateral_faults": 0,
          "wins": 4
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 74,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 37,
          "draws": 52,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "xiaomi/mimo-v2.5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-01T00:15:48Z",
          "losses": 4,
          "model": "xiaomi/mimo-v2.5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-7ad356726cce2b22",
          "rated_matches": 74,
          "raw_elo_rating": 1501.3005279978574,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "repaired",
          "score": 42.52868421147764,
          "uncertainty": 13.985026918962571,
          "unilateral_faults": 0,
          "wins": 18
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 70,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 35,
          "draws": 61,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "xiaomi/mimo-v2.5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T06:10:40Z",
          "losses": 6,
          "model": "xiaomi/mimo-v2.5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-d58c55e107783a21",
          "rated_matches": 70,
          "raw_elo_rating": 1463.8559190485062,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "repaired",
          "score": 36.62194410677851,
          "uncertainty": 15.58908290969266,
          "unilateral_faults": 0,
          "wins": 3
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 68,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 34,
          "draws": 52,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "xiaomi/mimo-v2.5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T06:10:40Z",
          "losses": 10,
          "model": "xiaomi/mimo-v2.5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-f8929b12716a2221",
          "rated_matches": 68,
          "raw_elo_rating": 1490.8209858823616,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "repaired",
          "score": 40.63045169882911,
          "uncertainty": 16.4429265428846,
          "unilateral_faults": 0,
          "wins": 6
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 96,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 46,
          "draws": 51,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "enabled",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "xiaomi/mimo-v2.5-pro",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 23,
          "model": "xiaomi/mimo-v2.5-pro",
          "point_rating_method": "sequential_elo",
          "public_id": "E-ffdebde8a72ed049",
          "rated_matches": 96,
          "raw_elo_rating": 1566.3530638646457,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "enabled",
          "repair_status": "repaired",
          "score": 53.300611514890754,
          "uncertainty": 7.017308256680951,
          "unilateral_faults": 0,
          "wins": 22
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 72,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 36,
          "draws": 53,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "z-ai/glm-5.2",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 10,
          "model": "z-ai/glm-5.2",
          "point_rating_method": "sequential_elo",
          "public_id": "E-1d5f5ff0402ff944",
          "rated_matches": 72,
          "raw_elo_rating": 1529.1774962447755,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "repaired",
          "score": 46.684607525873936,
          "uncertainty": 14.770573598065289,
          "unilateral_faults": 0,
          "wins": 9
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 66,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 33,
          "draws": 49,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "z-ai/glm-5.2",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-11T17:22:09Z",
          "losses": 10,
          "model": "z-ai/glm-5.2",
          "point_rating_method": "sequential_elo",
          "public_id": "E-912f31ad14c4bf0a",
          "rated_matches": 66,
          "raw_elo_rating": 1489.7254504864673,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "repaired",
          "score": 40.35454880564338,
          "uncertainty": 17.33472217815261,
          "unilateral_faults": 0,
          "wins": 7
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 82,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 41,
          "draws": 47,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "z-ai/glm-5.2",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-11T14:00:45Z",
          "losses": 19,
          "model": "z-ai/glm-5.2",
          "point_rating_method": "sequential_elo",
          "public_id": "E-f776c26a98306f5d",
          "rated_matches": 82,
          "raw_elo_rating": 1479.068861513742,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 39.48602607038318,
          "uncertainty": 11.132129994845172,
          "unilateral_faults": 0,
          "wins": 16
        }
      ],
      "GB2-05": [
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 100,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 43,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "xhigh",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-fable-5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 16,
          "model": "claude-fable-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-5aa4402ccce7b855",
          "rated_matches": 100,
          "raw_elo_rating": 2023.8636251018338,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "xhigh",
          "repair_status": "repaired",
          "score": 91.20233840190105,
          "uncertainty": 6.001859510499461,
          "unilateral_faults": 0,
          "wins": 84
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 106,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 53,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-fable-5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 42,
          "model": "claude-fable-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-ad7cf41c05ec3f64",
          "rated_matches": 106,
          "raw_elo_rating": 1679.6354629058385,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 62.71165398791373,
          "uncertainty": 4.586824452283178,
          "unilateral_faults": 0,
          "wins": 64
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 0,
          "capped_draws": 0,
          "coverage_status": "pending",
          "distinct_rated_opponents": 0,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "legacy_shared_thinking_budget",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-opus-4-5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "budget",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 0,
          "model": "claude-opus-4-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-7e9bc3ebc12ef500",
          "rated_matches": 0,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "budget",
          "reasoning_setting": "legacy_shared_thinking_budget",
          "repair_status": "first_pass",
          "unilateral_faults": 0,
          "wins": 0
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 106,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 53,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-opus-4-5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "omitted",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 40,
          "model": "claude-opus-4-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-934b5bc34a7e20b9",
          "rated_matches": 106,
          "raw_elo_rating": 1584.2090805580165,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "omitted",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 54.787452361508244,
          "uncertainty": 4.586824452283178,
          "unilateral_faults": 0,
          "wins": 66
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 200,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 75,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-opus-4-5",
            "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 91,
          "model": "claude-opus-4-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-a75e9d71efa4a6bc",
          "rated_matches": 200,
          "raw_elo_rating": 1557.6899839620967,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 53.45354337379487,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 109
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 200,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 67,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-opus-4-5",
            "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 86,
          "model": "claude-opus-4-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-ccacc93776fb7c88",
          "rated_matches": 200,
          "raw_elo_rating": 1510.738619126404,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "first_pass",
          "score": 49.55470457849347,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 114
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 0,
          "capped_draws": 0,
          "coverage_status": "pending",
          "distinct_rated_opponents": 0,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "legacy_shared_thinking_budget",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-opus-4-5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "budget",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 0,
          "model": "claude-opus-4-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-ff0722d17402bafa",
          "rated_matches": 0,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "budget",
          "reasoning_setting": "legacy_shared_thinking_budget",
          "repair_status": "first_pass",
          "unilateral_faults": 0,
          "wins": 0
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 98,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 49,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-opus-4-8",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "omitted",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 55,
          "model": "claude-opus-4-8",
          "point_rating_method": "sequential_elo",
          "public_id": "E-233f9cae6335e53d",
          "rated_matches": 98,
          "raw_elo_rating": 1386.8051899721886,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "omitted",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 38.26782236702627,
          "uncertainty": 6.501890762960602,
          "unilateral_faults": 0,
          "wins": 43
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 120,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 60,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "xhigh",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-opus-4-8",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 65,
          "model": "claude-opus-4-8",
          "point_rating_method": "sequential_elo",
          "public_id": "E-6774d700e60de31a",
          "rated_matches": 120,
          "raw_elo_rating": 1536.317407962045,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "xhigh",
          "repair_status": "repaired",
          "score": 51.00200589427959,
          "uncertainty": 1.7045454545454586,
          "unilateral_faults": 0,
          "wins": 55
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 122,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 59,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-opus-4-8",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 56,
          "model": "claude-opus-4-8",
          "point_rating_method": "sequential_elo",
          "public_id": "E-924d7e6ee41b562e",
          "rated_matches": 122,
          "raw_elo_rating": 1537.859169314774,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 51.154684162643335,
          "uncertainty": 1.3334817333716131,
          "unilateral_faults": 0,
          "wins": 66
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 120,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 60,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-opus-5",
            "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-25T10:50:00Z",
          "losses": 12,
          "model": "claude-opus-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-09963ffe0b0fa5fd",
          "rated_matches": 120,
          "raw_elo_rating": 1997.878157235796,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 89.32998553777773,
          "uncertainty": 1.7045454545454586,
          "unilateral_faults": 0,
          "wins": 108
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 114,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 57,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-opus-5",
            "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-25T10:50:00Z",
          "losses": 18,
          "model": "claude-opus-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-32c377b229530444",
          "rated_matches": 114,
          "raw_elo_rating": 1881.8264374761118,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 79.61528545204392,
          "uncertainty": 2.875240412015687,
          "unilateral_faults": 0,
          "wins": 96
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 70,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 29,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "xhigh",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-opus-5",
            "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-25T10:50:00Z",
          "losses": 0,
          "model": "claude-opus-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-3f3686d02d1503fa",
          "rated_matches": 70,
          "raw_elo_rating": 2137.478337961861,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "xhigh",
          "repair_status": "first_pass",
          "score": 100.0,
          "uncertainty": 15.58908290969266,
          "unilateral_faults": 0,
          "wins": 70
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 70,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 31,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "xhigh",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-opus-5",
            "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-25T10:50:00Z",
          "losses": 22,
          "model": "claude-opus-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-a35dfc1adc62e4eb",
          "rated_matches": 70,
          "raw_elo_rating": 1814.876197516069,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "xhigh",
          "repair_status": "first_pass",
          "score": 73.21113571418141,
          "uncertainty": 15.58908290969266,
          "unilateral_faults": 0,
          "wins": 48
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 118,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 59,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-opus-5",
            "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-25T10:50:00Z",
          "losses": 12,
          "model": "claude-opus-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-b53cb955b1d8baab",
          "rated_matches": 118,
          "raw_elo_rating": 1955.1194704180377,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 85.75403715058349,
          "uncertainty": 2.084924851410568,
          "unilateral_faults": 0,
          "wins": 106
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 112,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 56,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-opus-5",
            "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-25T10:50:00Z",
          "losses": 10,
          "model": "claude-opus-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-d7111b534ebcaba2",
          "rated_matches": 112,
          "raw_elo_rating": 1969.491951088303,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 86.86773451101418,
          "uncertainty": 3.286043419179858,
          "unilateral_faults": 0,
          "wins": 102
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 92,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 45,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-sonnet-5",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 63,
          "model": "claude-sonnet-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-66c9ddb5d274adfe",
          "rated_matches": 92,
          "raw_elo_rating": 1357.2618578161205,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 35.70854059047516,
          "uncertainty": 8.09758473652126,
          "unilateral_faults": 0,
          "wins": 29
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 94,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 45,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "xhigh",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-sonnet-5",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 39,
          "model": "claude-sonnet-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-750cee28d20157cb",
          "rated_matches": 94,
          "raw_elo_rating": 1522.3810009155313,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "xhigh",
          "repair_status": "first_pass",
          "score": 49.4564743296236,
          "uncertainty": 7.54891760425771,
          "unilateral_faults": 0,
          "wins": 55
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 92,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 44,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-sonnet-5",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 44,
          "model": "claude-sonnet-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-77d8a88f79b44f7d",
          "rated_matches": 92,
          "raw_elo_rating": 1481.5916885129375,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 46.03288300374409,
          "uncertainty": 8.09758473652126,
          "unilateral_faults": 0,
          "wins": 48
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 102,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 48,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "xhigh",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-sonnet-5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-03T16:50:00Z",
          "losses": 53,
          "model": "claude-sonnet-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-c902807aab849f31",
          "rated_matches": 102,
          "raw_elo_rating": 1584.3884545773712,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "xhigh",
          "repair_status": "first_pass",
          "score": 54.74058980227671,
          "uncertainty": 5.516463908214657,
          "unilateral_faults": 0,
          "wins": 49
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 104,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 50,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-sonnet-5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 38,
          "model": "claude-sonnet-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-e0a09b1ea3f11175",
          "rated_matches": 104,
          "raw_elo_rating": 1590.3103541790922,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 55.263664052390155,
          "uncertainty": 5.045003647426665,
          "unilateral_faults": 0,
          "wins": 66
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 100,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 50,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-sonnet-5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 46,
          "model": "claude-sonnet-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-e619c51e7d5d70d2",
          "rated_matches": 100,
          "raw_elo_rating": 1411.5046512373144,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 40.35208234845052,
          "uncertainty": 6.001859510499461,
          "unilateral_faults": 0,
          "wins": 54
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 82,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 41,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "unknown_legacy",
            "effective_request_value": "enabled",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "cohere/north-mini-code:free",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 36,
          "model": "cohere/north-mini-code",
          "point_rating_method": "sequential_elo",
          "public_id": "E-a0518a43c688d1e2",
          "rated_matches": 82,
          "raw_elo_rating": 1552.4350508377818,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "enabled",
          "repair_status": "first_pass",
          "score": 51.714121198453974,
          "uncertainty": 11.132129994845172,
          "unilateral_faults": 0,
          "wins": 46
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 78,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 39,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "deepseek/deepseek-v4-flash",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-01T00:15:48Z",
          "losses": 48,
          "model": "deepseek/deepseek-v4-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-06a41d0e11b18b77",
          "rated_matches": 78,
          "raw_elo_rating": 1312.647194208838,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 31.710988307007685,
          "uncertainty": 12.5043950463012,
          "unilateral_faults": 0,
          "wins": 30
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 114,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 57,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "deepseek/deepseek-v4-flash",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 64,
          "model": "deepseek/deepseek-v4-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-0dca18c79b6ac9d7",
          "rated_matches": 114,
          "raw_elo_rating": 1404.752960189545,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 39.99912971379366,
          "uncertainty": 2.875240412015687,
          "unilateral_faults": 0,
          "wins": 50
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 80,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 40,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "deepseek/deepseek-v4-flash",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T06:10:40Z",
          "losses": 45,
          "model": "deepseek/deepseek-v4-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-2c1cbd253f3a9d69",
          "rated_matches": 80,
          "raw_elo_rating": 1257.1871071905523,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 27.15201095688824,
          "uncertainty": 11.805555555555554,
          "unilateral_faults": 0,
          "wins": 35
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 102,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 49,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "xhigh",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "deepseek/deepseek-v4-flash",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 48,
          "model": "deepseek/deepseek-v4-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-b3d889b0631db85f",
          "rated_matches": 102,
          "raw_elo_rating": 1549.0224155741603,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "xhigh",
          "repair_status": "repaired",
          "score": 51.803795837193945,
          "uncertainty": 5.516463908214657,
          "unilateral_faults": 0,
          "wins": 54
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 98,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 45,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "xhigh",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "deepseek/deepseek-v4-pro",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 35,
          "model": "deepseek/deepseek-v4-pro",
          "point_rating_method": "sequential_elo",
          "public_id": "E-0ca4798825ceaccb",
          "rated_matches": 98,
          "raw_elo_rating": 1818.7116137409091,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "xhigh",
          "repair_status": "repaired",
          "score": 74.1333084252556,
          "uncertainty": 6.501890762960602,
          "unilateral_faults": 0,
          "wins": 63
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 98,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 49,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "deepseek/deepseek-v4-pro",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 50,
          "model": "deepseek/deepseek-v4-pro",
          "point_rating_method": "sequential_elo",
          "public_id": "E-da5f3b1a4e370e1a",
          "rated_matches": 98,
          "raw_elo_rating": 1393.141045545112,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "repaired",
          "score": 38.79395147095302,
          "uncertainty": 6.501890762960602,
          "unilateral_faults": 0,
          "wins": 48
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 98,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 49,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "google/gemini-3.1-flash-lite",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 70,
          "model": "google/gemini-3.1-flash-lite",
          "point_rating_method": "sequential_elo",
          "public_id": "E-7603462aff103041",
          "rated_matches": 98,
          "raw_elo_rating": 1196.77816581129,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "repaired",
          "score": 22.487988563537684,
          "uncertainty": 6.501890762960602,
          "unilateral_faults": 0,
          "wins": 28
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 88,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 43,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "google/gemini-3.1-flash-lite",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 70,
          "model": "google/gemini-3.1-flash-lite",
          "point_rating_method": "sequential_elo",
          "public_id": "E-a72dd193e1dc4331",
          "rated_matches": 88,
          "raw_elo_rating": 1165.8540579796686,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "repaired",
          "score": 19.73749709047673,
          "uncertainty": 9.249894000318006,
          "unilateral_faults": 0,
          "wins": 18
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 78,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 39,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "google/gemini-3.1-flash-lite",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 59,
          "model": "google/gemini-3.1-flash-lite",
          "point_rating_method": "sequential_elo",
          "public_id": "E-d979b43c3aeea657",
          "rated_matches": 78,
          "raw_elo_rating": 1136.308456520139,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 17.067829071463514,
          "uncertainty": 12.5043950463012,
          "unilateral_faults": 0,
          "wins": 19
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 0,
          "capped_draws": 0,
          "coverage_status": "pending",
          "distinct_rated_opponents": 0,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "low",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "google/gemini-3.5-flash",
            "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-21T14:20:15Z",
          "losses": 0,
          "model": "google/gemini-3.5-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-a13c4c9fdf6b244d",
          "rated_matches": 0,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "low",
          "repair_status": "first_pass",
          "unilateral_faults": 0,
          "wins": 0
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 112,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 56,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "google/gemini-3.5-flash",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 54,
          "model": "google/gemini-3.5-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-a7ce764239377b3f",
          "rated_matches": 112,
          "raw_elo_rating": 1553.2266000489765,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "repaired",
          "score": 52.301082285856566,
          "uncertainty": 3.286043419179858,
          "unilateral_faults": 0,
          "wins": 58
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 100,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 49,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "google/gemini-3.5-flash",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 55,
          "model": "google/gemini-3.5-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-b50da126631c1ea1",
          "rated_matches": 100,
          "raw_elo_rating": 1552.7470805088597,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "repaired",
          "score": 52.08084603218233,
          "uncertainty": 6.001859510499461,
          "unilateral_faults": 0,
          "wins": 45
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 150,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 52,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "google/gemini-3.5-flash-lite",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 110,
          "model": "google/gemini-3.5-flash-lite",
          "point_rating_method": "sequential_elo",
          "public_id": "E-06abb3c93d2072c8",
          "rated_matches": 150,
          "raw_elo_rating": 1256.6289119553658,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "first_pass",
          "score": 28.093244733221475,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 40
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 166,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 60,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "minimal",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "google/gemini-3.5-flash-lite",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 141,
          "model": "google/gemini-3.5-flash-lite",
          "point_rating_method": "sequential_elo",
          "public_id": "E-214f636367cbdac4",
          "rated_matches": 164,
          "raw_elo_rating": 1069.3768340544518,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "minimal",
          "repair_status": "repaired",
          "score": 12.661059892346074,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 23
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 162,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 61,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "google/gemini-3.5-flash-lite",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 131,
          "model": "google/gemini-3.5-flash-lite",
          "point_rating_method": "sequential_elo",
          "public_id": "E-3dd83d6fa9f8f758",
          "rated_matches": 162,
          "raw_elo_rating": 1104.9629752879334,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 15.600315327273428,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 31
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 150,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 53,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "google/gemini-3.5-flash-lite",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 112,
          "model": "google/gemini-3.5-flash-lite",
          "point_rating_method": "sequential_elo",
          "public_id": "E-5b803013ec40d15d",
          "rated_matches": 150,
          "raw_elo_rating": 1163.2464253090598,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "first_pass",
          "score": 20.338768095269625,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 38
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 164,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 62,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "google/gemini-3.5-flash-lite",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 128,
          "model": "google/gemini-3.5-flash-lite",
          "point_rating_method": "sequential_elo",
          "public_id": "E-8826ab29e7591ece",
          "rated_matches": 164,
          "raw_elo_rating": 1126.374330356309,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 17.394128900976742,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 36
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 160,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 58,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "minimal",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "google/gemini-3.5-flash-lite",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 136,
          "model": "google/gemini-3.5-flash-lite",
          "point_rating_method": "sequential_elo",
          "public_id": "E-a870d09d3e1a40d4",
          "rated_matches": 160,
          "raw_elo_rating": 988.2545815273319,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "minimal",
          "repair_status": "first_pass",
          "score": 5.8927470205869374,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 24
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 162,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 66,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "google/gemini-3.6-flash",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 7,
          "model": "google/gemini-3.6-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-5bcc61f900210bfa",
          "rated_matches": 162,
          "raw_elo_rating": 2029.54027540886,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 92.37716429814988,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 155
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 146,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 56,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "google/gemini-3.6-flash",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 9,
          "model": "google/gemini-3.6-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-8b9ff59d79afb558",
          "rated_matches": 146,
          "raw_elo_rating": 2021.9160560630553,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "first_pass",
          "score": 91.60611803088719,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 137
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 159,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 65,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "minimal",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "google/gemini-3.6-flash",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 73,
          "model": "google/gemini-3.6-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-9bef179ce22a6c93",
          "rated_matches": 159,
          "raw_elo_rating": 1578.2068383181902,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "minimal",
          "repair_status": "first_pass",
          "score": 54.874182662406035,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 86
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 142,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 55,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "google/gemini-3.6-flash",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 35,
          "model": "google/gemini-3.6-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-c4f143aad203feb3",
          "rated_matches": 142,
          "raw_elo_rating": 1814.6990927676245,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "first_pass",
          "score": 74.3607806821286,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 107
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 162,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 66,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "google/gemini-3.6-flash",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 75,
          "model": "google/gemini-3.6-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-d95a1da824d70f6d",
          "rated_matches": 162,
          "raw_elo_rating": 1510.5926868235526,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 49.28378462356395,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 87
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 182,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 68,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "minimal",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "google/gemini-3.6-flash",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 75,
          "model": "google/gemini-3.6-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-e23af86eb5787555",
          "rated_matches": 182,
          "raw_elo_rating": 1432.2294603476682,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "minimal",
          "repair_status": "first_pass",
          "score": 42.922786979189105,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 107
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 94,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 47,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "google/gemma-4-31b-it",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 67,
          "model": "google/gemma-4-31b-it",
          "point_rating_method": "sequential_elo",
          "public_id": "E-e8e17fbbdd12faa4",
          "rated_matches": 94,
          "raw_elo_rating": 1136.0733751755404,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 17.377509992236185,
          "uncertainty": 7.54891760425771,
          "unilateral_faults": 0,
          "wins": 27
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 124,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 57,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "enabled",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "google/gemma-4-31b-it",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 58,
          "model": "google/gemma-4-31b-it",
          "point_rating_method": "sequential_elo",
          "public_id": "E-fd1bc1e2e6ac48fb",
          "rated_matches": 124,
          "raw_elo_rating": 1583.880968834933,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "enabled",
          "repair_status": "repaired",
          "score": 55.00038838965367,
          "uncertainty": 0.9713595499957961,
          "unilateral_faults": 0,
          "wins": 66
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 94,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 47,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-4.1",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "omitted",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 66,
          "model": "gpt-4.1",
          "point_rating_method": "sequential_elo",
          "public_id": "E-1b9f1f7b70f02927",
          "rated_matches": 94,
          "raw_elo_rating": 1135.4295707705774,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "omitted",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 17.324048509285905,
          "uncertainty": 7.54891760425771,
          "unilateral_faults": 0,
          "wins": 28
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 102,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 51,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 52,
          "model": "gpt-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-9e5b308c41a36374",
          "rated_matches": 102,
          "raw_elo_rating": 1607.1651624106053,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 56.63196638824444,
          "uncertainty": 5.516463908214657,
          "unilateral_faults": 0,
          "wins": 50
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 102,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 45,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 47,
          "model": "gpt-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-c5ad048b6fb4e93d",
          "rated_matches": 102,
          "raw_elo_rating": 1681.8135849530192,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "first_pass",
          "score": 62.830767356755665,
          "uncertainty": 5.516463908214657,
          "unilateral_faults": 0,
          "wins": 55
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 0,
          "capped_draws": 0,
          "coverage_status": "pending",
          "distinct_rated_opponents": 0,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "low",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5",
            "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-21T14:20:15Z",
          "losses": 0,
          "model": "gpt-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-d03d2c6a69fc3e16",
          "rated_matches": 0,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "low",
          "repair_status": "repaired",
          "unilateral_faults": 0,
          "wins": 0
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 96,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 44,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.4",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 17,
          "model": "gpt-5.4",
          "point_rating_method": "sequential_elo",
          "public_id": "E-34e3865fc087a754",
          "rated_matches": 96,
          "raw_elo_rating": 1843.4523646471466,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 76.15353884909591,
          "uncertainty": 7.017308256680951,
          "unilateral_faults": 0,
          "wins": 79
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 92,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 46,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.4",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 25,
          "model": "gpt-5.4",
          "point_rating_method": "sequential_elo",
          "public_id": "E-6d3546010ef68f50",
          "rated_matches": 92,
          "raw_elo_rating": 1797.5895875968265,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "repaired",
          "score": 72.27333144424207,
          "uncertainty": 8.09758473652126,
          "unilateral_faults": 0,
          "wins": 67
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 90,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 43,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.4",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 32,
          "model": "gpt-5.4",
          "point_rating_method": "sequential_elo",
          "public_id": "E-a09c0b14cae46193",
          "rated_matches": 90,
          "raw_elo_rating": 1567.0954010065689,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 53.09546252248944,
          "uncertainty": 8.664241836095918,
          "unilateral_faults": 0,
          "wins": 58
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 120,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 60,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.4",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 70,
          "model": "gpt-5.4",
          "point_rating_method": "sequential_elo",
          "public_id": "E-cafab3c275850d3b",
          "rated_matches": 120,
          "raw_elo_rating": 1461.6644809842144,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 44.802830877695115,
          "uncertainty": 1.7045454545454586,
          "unilateral_faults": 0,
          "wins": 50
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 94,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 44,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "xhigh",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.4",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 1,
          "model": "gpt-5.4",
          "point_rating_method": "sequential_elo",
          "public_id": "E-dcce778d7a3114fa",
          "rated_matches": 94,
          "raw_elo_rating": 1994.8915096393325,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "xhigh",
          "repair_status": "first_pass",
          "score": 88.69372140533535,
          "uncertainty": 7.54891760425771,
          "unilateral_faults": 0,
          "wins": 93
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 94,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 43,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "xhigh",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.4",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 8,
          "model": "gpt-5.4",
          "point_rating_method": "sequential_elo",
          "public_id": "E-f6403f7a30e19e82",
          "rated_matches": 94,
          "raw_elo_rating": 2048.0082481553145,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "xhigh",
          "repair_status": "first_pass",
          "score": 93.10453249742434,
          "uncertainty": 7.54891760425771,
          "unilateral_faults": 0,
          "wins": 86
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 124,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 58,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.4-mini",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 50,
          "model": "gpt-5.4-mini",
          "point_rating_method": "sequential_elo",
          "public_id": "E-0791f6b66243ec1a",
          "rated_matches": 124,
          "raw_elo_rating": 1576.1336146218378,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 54.357048515026754,
          "uncertainty": 0.9713595499957961,
          "unilateral_faults": 0,
          "wins": 74
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 94,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 47,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.4-mini",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 66,
          "model": "gpt-5.4-mini",
          "point_rating_method": "sequential_elo",
          "public_id": "E-427bdffeacc6c394",
          "rated_matches": 94,
          "raw_elo_rating": 1258.1950094624974,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "repaired",
          "score": 27.518483895121314,
          "uncertainty": 7.54891760425771,
          "unilateral_faults": 0,
          "wins": 28
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 88,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 44,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.4-nano",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-09T17:30:50Z",
          "losses": 67,
          "model": "gpt-5.4-nano",
          "point_rating_method": "sequential_elo",
          "public_id": "E-3311575b341ee4a8",
          "rated_matches": 88,
          "raw_elo_rating": 1193.8351500708243,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "repaired",
          "score": 22.061045463600173,
          "uncertainty": 9.249894000318006,
          "unilateral_faults": 0,
          "wins": 21
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 90,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 45,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.4-nano",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 69,
          "model": "gpt-5.4-nano",
          "point_rating_method": "sequential_elo",
          "public_id": "E-6c37eeef15b82287",
          "rated_matches": 90,
          "raw_elo_rating": 1144.518195047545,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "repaired",
          "score": 18.004674206350256,
          "uncertainty": 8.664241836095918,
          "unilateral_faults": 0,
          "wins": 21
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 92,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 46,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.4-nano",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 17,
          "model": "gpt-5.4-nano",
          "point_rating_method": "sequential_elo",
          "public_id": "E-8e40431df091d53f",
          "rated_matches": 92,
          "raw_elo_rating": 1819.1047661903833,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 74.05995071041148,
          "uncertainty": 8.09758473652126,
          "unilateral_faults": 0,
          "wins": 75
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 116,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 57,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.4-nano",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-09T17:30:50Z",
          "losses": 79,
          "model": "gpt-5.4-nano",
          "point_rating_method": "sequential_elo",
          "public_id": "E-a0d8c8fd6b01598c",
          "rated_matches": 116,
          "raw_elo_rating": 1253.3051649919003,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 27.449500663218604,
          "uncertainty": 2.4750163521024238,
          "unilateral_faults": 0,
          "wins": 37
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 92,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 46,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 40,
          "model": "gpt-5.5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-6f42dbbf02274b56",
          "rated_matches": 92,
          "raw_elo_rating": 1551.1627362890197,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 51.810059046408426,
          "uncertainty": 8.09758473652126,
          "unilateral_faults": 0,
          "wins": 52
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 98,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 45,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "xhigh",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 21,
          "model": "gpt-5.5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-762e9d80a60b41ed",
          "rated_matches": 98,
          "raw_elo_rating": 1927.4799055461476,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "xhigh",
          "repair_status": "first_pass",
          "score": 83.16542149104123,
          "uncertainty": 6.501890762960602,
          "unilateral_faults": 0,
          "wins": 77
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 98,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 49,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 31,
          "model": "gpt-5.5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-ffa82d1e96e897ab",
          "rated_matches": 98,
          "raw_elo_rating": 1717.6614023179375,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 65.742104336769,
          "uncertainty": 6.501890762960602,
          "unilateral_faults": 0,
          "wins": 67
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 108,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 52,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "xhigh",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.6-luna",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-10T05:30:29Z",
          "losses": 57,
          "model": "gpt-5.6-luna",
          "point_rating_method": "sequential_elo",
          "public_id": "E-25a83ddaeb1268a4",
          "rated_matches": 108,
          "raw_elo_rating": 1629.976691086905,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "xhigh",
          "repair_status": "first_pass",
          "score": 58.61758837696586,
          "uncertainty": 4.1413142610575715,
          "unilateral_faults": 0,
          "wins": 51
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 94,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 44,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "xhigh",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.6-luna",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 35,
          "model": "gpt-5.6-luna",
          "point_rating_method": "sequential_elo",
          "public_id": "E-3b8df7a8d128f873",
          "rated_matches": 94,
          "raw_elo_rating": 1585.7142254237854,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "xhigh",
          "repair_status": "first_pass",
          "score": 54.71566186567154,
          "uncertainty": 7.54891760425771,
          "unilateral_faults": 0,
          "wins": 59
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 88,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 43,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.6-luna",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-10T05:30:29Z",
          "losses": 79,
          "model": "gpt-5.6-luna",
          "point_rating_method": "sequential_elo",
          "public_id": "E-59156a669808a24f",
          "rated_matches": 86,
          "raw_elo_rating": 997.5922414110602,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "repaired",
          "score": 5.724804936416754,
          "uncertainty": 9.855626741889738,
          "unilateral_faults": 2,
          "wins": 7
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 92,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 43,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.6-luna",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 59,
          "model": "gpt-5.6-luna",
          "point_rating_method": "sequential_elo",
          "public_id": "E-6879be00992f95f0",
          "rated_matches": 92,
          "raw_elo_rating": 1273.8587217985935,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 28.782748688729765,
          "uncertainty": 8.09758473652126,
          "unilateral_faults": 0,
          "wins": 33
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 93,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 44,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.6-luna",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 49,
          "model": "gpt-5.6-luna",
          "point_rating_method": "sequential_elo",
          "public_id": "E-8056d7cf3d4b6248",
          "rated_matches": 93,
          "raw_elo_rating": 1470.8329908962558,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 45.15785126150731,
          "uncertainty": 7.821062312939668,
          "unilateral_faults": 0,
          "wins": 44
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 116,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 58,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.6-luna",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-10T05:30:29Z",
          "losses": 59,
          "model": "gpt-5.6-luna",
          "point_rating_method": "sequential_elo",
          "public_id": "E-e917387a1c57aa23",
          "rated_matches": 116,
          "raw_elo_rating": 1602.8775455457373,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 56.477972228182814,
          "uncertainty": 2.4750163521024238,
          "unilateral_faults": 0,
          "wins": 57
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 88,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 43,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "xhigh",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.6-sol",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 23,
          "model": "gpt-5.6-sol",
          "point_rating_method": "sequential_elo",
          "public_id": "E-225037bcf869a775",
          "rated_matches": 88,
          "raw_elo_rating": 1649.8907644291016,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "xhigh",
          "repair_status": "first_pass",
          "score": 59.931879001613865,
          "uncertainty": 9.249894000318006,
          "unilateral_faults": 0,
          "wins": 65
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 98,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 49,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.6-sol",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-10T05:30:29Z",
          "losses": 39,
          "model": "gpt-5.6-sol",
          "point_rating_method": "sequential_elo",
          "public_id": "E-471e9297eea18ffd",
          "rated_matches": 98,
          "raw_elo_rating": 1665.4347956065355,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 61.405209741565095,
          "uncertainty": 6.501890762960602,
          "unilateral_faults": 0,
          "wins": 59
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 94,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 44,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "xhigh",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.6-sol",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-10T05:30:29Z",
          "losses": 34,
          "model": "gpt-5.6-sol",
          "point_rating_method": "sequential_elo",
          "public_id": "E-af9c2c2998294ad0",
          "rated_matches": 94,
          "raw_elo_rating": 1744.4095445478265,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "xhigh",
          "repair_status": "first_pass",
          "score": 67.89371257833555,
          "uncertainty": 7.54891760425771,
          "unilateral_faults": 0,
          "wins": 60
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 94,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 44,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.6-sol",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 17,
          "model": "gpt-5.6-sol",
          "point_rating_method": "sequential_elo",
          "public_id": "E-c9acd4a3fb993f97",
          "rated_matches": 94,
          "raw_elo_rating": 1809.7744136870645,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 73.32160777460308,
          "uncertainty": 7.54891760425771,
          "unilateral_faults": 0,
          "wins": 77
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 90,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 43,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.6-sol",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 36,
          "model": "gpt-5.6-sol",
          "point_rating_method": "sequential_elo",
          "public_id": "E-d29c6c5eb08da2d9",
          "rated_matches": 90,
          "raw_elo_rating": 1509.1321010535598,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 48.282193230929145,
          "uncertainty": 8.664241836095918,
          "unilateral_faults": 0,
          "wins": 54
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 98,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 49,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.6-sol",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-10T05:30:29Z",
          "losses": 37,
          "model": "gpt-5.6-sol",
          "point_rating_method": "sequential_elo",
          "public_id": "E-d61f8454991c5422",
          "rated_matches": 98,
          "raw_elo_rating": 1676.2772256568912,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 62.30556454623592,
          "uncertainty": 6.501890762960602,
          "unilateral_faults": 0,
          "wins": 61
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 98,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 45,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "xhigh",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.6-terra",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-10T05:30:29Z",
          "losses": 42,
          "model": "gpt-5.6-terra",
          "point_rating_method": "sequential_elo",
          "public_id": "E-012ecb9ce0709c05",
          "rated_matches": 98,
          "raw_elo_rating": 1679.100259521219,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "xhigh",
          "repair_status": "repaired",
          "score": 62.53998912556835,
          "uncertainty": 6.501890762960602,
          "unilateral_faults": 0,
          "wins": 56
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 92,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 46,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.6-terra",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-10T05:30:29Z",
          "losses": 38,
          "model": "gpt-5.6-terra",
          "point_rating_method": "sequential_elo",
          "public_id": "E-1f00b423eab1c19d",
          "rated_matches": 92,
          "raw_elo_rating": 1567.3066590038927,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 53.15064951506388,
          "uncertainty": 8.09758473652126,
          "unilateral_faults": 0,
          "wins": 54
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 110,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 52,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.6-terra",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-10T05:30:29Z",
          "losses": 45,
          "model": "gpt-5.6-terra",
          "point_rating_method": "sequential_elo",
          "public_id": "E-9664e98d37ece097",
          "rated_matches": 110,
          "raw_elo_rating": 1609.1466507381233,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 56.91665552510462,
          "uncertainty": 3.707899787624953,
          "unilateral_faults": 0,
          "wins": 65
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 94,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 46,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "meituan/longcat-2.0",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 71,
          "model": "meituan/longcat-2.0",
          "point_rating_method": "sequential_elo",
          "public_id": "E-067ab716d64e3e9a",
          "rated_matches": 92,
          "raw_elo_rating": 1093.8498238628247,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "none",
          "repair_status": "repaired",
          "score": 13.834819544870367,
          "uncertainty": 8.09758473652126,
          "unilateral_faults": 2,
          "wins": 21
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 172,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 62,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "enabled",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "meituan/longcat-2.0",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 60,
          "model": "meituan/longcat-2.0",
          "point_rating_method": "sequential_elo",
          "public_id": "E-73a7ad076eeaa6ae",
          "rated_matches": 172,
          "raw_elo_rating": 1665.397646233429,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "enabled",
          "repair_status": "first_pass",
          "score": 62.2150922209429,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 112
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 170,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 63,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "enabled",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "meituan/longcat-2.0",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 130,
          "model": "meituan/longcat-2.0",
          "point_rating_method": "sequential_elo",
          "public_id": "E-8b7eb63d4f53d846",
          "rated_matches": 170,
          "raw_elo_rating": 1167.4814201454985,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "enabled",
          "repair_status": "first_pass",
          "score": 20.85343047035033,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 40
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 88,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 43,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "meituan/longcat-2.0",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 59,
          "model": "meituan/longcat-2.0",
          "point_rating_method": "sequential_elo",
          "public_id": "E-8cc657b7db4428cb",
          "rated_matches": 86,
          "raw_elo_rating": 1113.7152262954376,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 15.36765131751343,
          "uncertainty": 9.855626741889738,
          "unilateral_faults": 2,
          "wins": 27
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 92,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 43,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "minimal",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "meta/muse-spark-1.2",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-08-13T16:58:34Z",
          "losses": 42,
          "model": "meta/muse-spark-1.2",
          "point_rating_method": "sequential_elo",
          "public_id": "E-1fbf9ab6a0c6d3ee",
          "rated_matches": 92,
          "raw_elo_rating": 1565.788333723547,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "minimal",
          "repair_status": "first_pass",
          "score": 53.02456786594432,
          "uncertainty": 8.09758473652126,
          "unilateral_faults": 0,
          "wins": 50
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 94,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 44,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "meta/muse-spark-1.2",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-08-13T16:58:34Z",
          "losses": 41,
          "model": "meta/muse-spark-1.2",
          "point_rating_method": "sequential_elo",
          "public_id": "E-782ab5805e8c7fe1",
          "rated_matches": 94,
          "raw_elo_rating": 1554.8886887946508,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 52.15591097203426,
          "uncertainty": 7.54891760425771,
          "unilateral_faults": 0,
          "wins": 53
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 114,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 57,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "minimax/minimax-m3",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 58,
          "model": "minimax/minimax-m3",
          "point_rating_method": "sequential_elo",
          "public_id": "E-33797d7b77c7800c",
          "rated_matches": 114,
          "raw_elo_rating": 1467.3464738181478,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "none",
          "repair_status": "repaired",
          "score": 45.19689169842294,
          "uncertainty": 2.875240412015687,
          "unilateral_faults": 0,
          "wins": 56
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 106,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 52,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "enabled",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "minimax/minimax-m3",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 103,
          "model": "minimax/minimax-m3",
          "point_rating_method": "sequential_elo",
          "public_id": "E-fb8ac45946e32e22",
          "rated_matches": 106,
          "raw_elo_rating": 924.4368254590598,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "enabled",
          "repair_status": "repaired",
          "score": 0.0,
          "uncertainty": 4.586824452283178,
          "unilateral_faults": 0,
          "wins": 3
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 90,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 45,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "mistralai/mistral-medium-3-5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 65,
          "model": "mistralai/mistral-medium-3-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-1954b83d439b455c",
          "rated_matches": 90,
          "raw_elo_rating": 1231.6665190864155,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "repaired",
          "score": 25.241466318726623,
          "uncertainty": 8.664241836095918,
          "unilateral_faults": 0,
          "wins": 25
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 98,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 49,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "mistralai/mistral-medium-3-5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 52,
          "model": "mistralai/mistral-medium-3-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-4a7d37b86196302f",
          "rated_matches": 98,
          "raw_elo_rating": 1351.468176625996,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 35.33343869093166,
          "uncertainty": 6.501890762960602,
          "unilateral_faults": 0,
          "wins": 46
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 108,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 53,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "enabled",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "moonshotai/kimi-k2.7-code",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 51,
          "model": "moonshotai/kimi-k2.7-code",
          "point_rating_method": "sequential_elo",
          "public_id": "E-952fba19b28982d5",
          "rated_matches": 108,
          "raw_elo_rating": 1601.2213719654865,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "enabled",
          "repair_status": "repaired",
          "score": 56.229748233144726,
          "uncertainty": 4.1413142610575715,
          "unilateral_faults": 0,
          "wins": 57
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 185,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 77,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "low",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "moonshotai/kimi-k3",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T14:00:00Z",
          "losses": 65,
          "model": "moonshotai/kimi-k3",
          "point_rating_method": "sequential_elo",
          "public_id": "E-4419230379dcd41e",
          "rated_matches": 185,
          "raw_elo_rating": 1633.2331677471427,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "low",
          "repair_status": "first_pass",
          "score": 59.63400603920557,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 120
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 176,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 62,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "moonshotai/kimi-k3",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T14:00:00Z",
          "losses": 70,
          "model": "moonshotai/kimi-k3",
          "point_rating_method": "sequential_elo",
          "public_id": "E-895556dde47644ae",
          "rated_matches": 176,
          "raw_elo_rating": 1544.3586605576277,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "first_pass",
          "score": 52.19271965091757,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 106
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 106,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 52,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "enabled",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "nex-agi/nex-n2-pro",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 74,
          "model": "nex-agi/nex-n2-pro",
          "point_rating_method": "sequential_elo",
          "public_id": "E-5f76f577111bee8d",
          "rated_matches": 106,
          "raw_elo_rating": 1281.5487586993647,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "enabled",
          "repair_status": "repaired",
          "score": 29.654555612064655,
          "uncertainty": 4.586824452283178,
          "unilateral_faults": 0,
          "wins": 32
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 106,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 53,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "nex-agi/nex-n2-pro",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-11T17:22:09Z",
          "losses": 53,
          "model": "nex-agi/nex-n2-pro",
          "point_rating_method": "sequential_elo",
          "public_id": "E-962a9da8812a74d4",
          "rated_matches": 106,
          "raw_elo_rating": 1463.6103813613147,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "none",
          "repair_status": "repaired",
          "score": 44.77294290610812,
          "uncertainty": 4.586824452283178,
          "unilateral_faults": 0,
          "wins": 53
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 88,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 44,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "nvidia/nemotron-3-ultra-550b-a55b",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 33,
          "model": "nvidia/nemotron-3-ultra-550b-a55b",
          "point_rating_method": "sequential_elo",
          "public_id": "E-4477e0de2e04aad4",
          "rated_matches": 88,
          "raw_elo_rating": 1593.0579629263639,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 55.212486240190024,
          "uncertainty": 9.249894000318006,
          "unilateral_faults": 0,
          "wins": 55
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 112,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 53,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "nvidia/nemotron-3-ultra-550b-a55b",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 68,
          "model": "nvidia/nemotron-3-ultra-550b-a55b",
          "point_rating_method": "sequential_elo",
          "public_id": "E-48ed5c5e00ef38fb",
          "rated_matches": 112,
          "raw_elo_rating": 1422.3746295977035,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "first_pass",
          "score": 41.43514174030673,
          "uncertainty": 3.286043419179858,
          "unilateral_faults": 0,
          "wins": 44
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 98,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 49,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "nvidia/nemotron-3-ultra-550b-a55b",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-11T17:22:09Z",
          "losses": 54,
          "model": "nvidia/nemotron-3-ultra-550b-a55b",
          "point_rating_method": "sequential_elo",
          "public_id": "E-da3b98638ff53ea9",
          "rated_matches": 98,
          "raw_elo_rating": 1460.5213788610474,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "repaired",
          "score": 44.38921070339174,
          "uncertainty": 6.501890762960602,
          "unilateral_faults": 0,
          "wins": 44
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 114,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 56,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "o3",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 50,
          "model": "o3",
          "point_rating_method": "sequential_elo",
          "public_id": "E-343b92f3dda3dcb5",
          "rated_matches": 114,
          "raw_elo_rating": 1505.8097339730377,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 48.39087874034282,
          "uncertainty": 2.875240412015687,
          "unilateral_faults": 0,
          "wins": 64
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 159,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 63,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "o3",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 61,
          "model": "o3",
          "point_rating_method": "sequential_elo",
          "public_id": "E-4724b57e861c4ecf",
          "rated_matches": 159,
          "raw_elo_rating": 1655.548273394007,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "first_pass",
          "score": 61.29661124596546,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 98
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 172,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 62,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "o3",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-03T16:00:00Z",
          "losses": 92,
          "model": "o3",
          "point_rating_method": "sequential_elo",
          "public_id": "E-61d05a26a332d2e5",
          "rated_matches": 172,
          "raw_elo_rating": 1474.0668126827427,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "first_pass",
          "score": 46.326990156278704,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 80
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 151,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 55,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "o3",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-03T15:45:00Z",
          "losses": 82,
          "model": "o3",
          "point_rating_method": "sequential_elo",
          "public_id": "E-9bfe5e29476019eb",
          "rated_matches": 151,
          "raw_elo_rating": 1405.0942815728604,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "first_pass",
          "score": 40.430707369140535,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 69
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 152,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 52,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "o3",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-03T15:50:00Z",
          "losses": 57,
          "model": "o3",
          "point_rating_method": "sequential_elo",
          "public_id": "E-ffb183b7ecfe85e0",
          "rated_matches": 152,
          "raw_elo_rating": 1567.5529820460479,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "first_pass",
          "score": 53.93008798138243,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 95
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 189,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 71,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "low",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "openai/gpt-oss-120b",
            "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-21T14:20:15Z",
          "losses": 153,
          "model": "openai/gpt-oss-120b",
          "point_rating_method": "sequential_elo",
          "public_id": "E-172336d3fd38632a",
          "rated_matches": 189,
          "raw_elo_rating": 1087.1904502695809,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "low",
          "repair_status": "repaired",
          "score": 14.31642168470547,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 36
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 116,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 56,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "openai/gpt-oss-120b",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 67,
          "model": "openai/gpt-oss-120b",
          "point_rating_method": "sequential_elo",
          "public_id": "E-5ef540286ecbb63d",
          "rated_matches": 116,
          "raw_elo_rating": 1456.517503684909,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "repaired",
          "score": 44.324242271963605,
          "uncertainty": 2.4750163521024238,
          "unilateral_faults": 0,
          "wins": 49
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 102,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 51,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "poolside/laguna-s-2.1",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 24,
          "model": "poolside/laguna-s-2.1",
          "point_rating_method": "sequential_elo",
          "public_id": "E-1ca53619662c7f6f",
          "rated_matches": 102,
          "raw_elo_rating": 1818.408828937755,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 74.17362902574152,
          "uncertainty": 5.516463908214657,
          "unilateral_faults": 0,
          "wins": 78
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 94,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 47,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "poolside/laguna-s-2.1",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 47,
          "model": "poolside/laguna-s-2.1",
          "point_rating_method": "sequential_elo",
          "public_id": "E-21623e96b2b104e9",
          "rated_matches": 94,
          "raw_elo_rating": 1353.7896159286227,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "none",
          "repair_status": "repaired",
          "score": 35.45665484320768,
          "uncertainty": 7.54891760425771,
          "unilateral_faults": 0,
          "wins": 47
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 176,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 67,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "enabled",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "poolside/laguna-s-2.1",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 138,
          "model": "poolside/laguna-s-2.1",
          "point_rating_method": "sequential_elo",
          "public_id": "E-53ce0020411c86d4",
          "rated_matches": 176,
          "raw_elo_rating": 1135.820841482102,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "enabled",
          "repair_status": "first_pass",
          "score": 18.267761261878103,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 38
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 199,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 71,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "enabled",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "poolside/laguna-s-2.1",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 114,
          "model": "poolside/laguna-s-2.1",
          "point_rating_method": "sequential_elo",
          "public_id": "E-62e15a037ee860c1",
          "rated_matches": 199,
          "raw_elo_rating": 1462.2792203523072,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "enabled",
          "repair_status": "repaired",
          "score": 45.52478884360916,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 85
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 124,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 59,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "enabled",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "qwen/qwen3.7-max",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 63,
          "model": "qwen/qwen3.7-max",
          "point_rating_method": "sequential_elo",
          "public_id": "E-435ec29661cdc285",
          "rated_matches": 124,
          "raw_elo_rating": 1544.3386733865298,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "enabled",
          "repair_status": "repaired",
          "score": 51.71679831534971,
          "uncertainty": 0.9713595499957961,
          "unilateral_faults": 0,
          "wins": 61
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 106,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 53,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "qwen/qwen3.7-max",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 53,
          "model": "qwen/qwen3.7-max",
          "point_rating_method": "sequential_elo",
          "public_id": "E-c577c41440c17864",
          "rated_matches": 106,
          "raw_elo_rating": 1515.586736592979,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 49.08905663197634,
          "uncertainty": 4.586824452283178,
          "unilateral_faults": 0,
          "wins": 53
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 124,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 58,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "enabled",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "qwen/qwen3.7-plus",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 64,
          "model": "qwen/qwen3.7-plus",
          "point_rating_method": "sequential_elo",
          "public_id": "E-6cc7454f585005c4",
          "rated_matches": 124,
          "raw_elo_rating": 1607.3794802947366,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "enabled",
          "repair_status": "repaired",
          "score": 56.95170350971318,
          "uncertainty": 0.9713595499957961,
          "unilateral_faults": 0,
          "wins": 60
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 102,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 51,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "qwen/qwen3.7-plus",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 54,
          "model": "qwen/qwen3.7-plus",
          "point_rating_method": "sequential_elo",
          "public_id": "E-94daaf1196d89c6c",
          "rated_matches": 102,
          "raw_elo_rating": 1476.341736666781,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 45.76839619365652,
          "uncertainty": 5.516463908214657,
          "unilateral_faults": 0,
          "wins": 48
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 20,
          "capped_draws": 0,
          "coverage_status": "under_covered",
          "distinct_rated_opponents": 11,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "qwen/qwen3.8-max",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 8,
          "model": "qwen/qwen3.8-max",
          "point_rating_method": "sequential_elo",
          "public_id": "E-2dec08c905be48b9",
          "rated_matches": 20,
          "raw_elo_rating": 1577.631160970109,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 50.2040113856351,
          "uncertainty": 65.3589451179962,
          "unilateral_faults": 0,
          "wins": 12
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 17,
          "capped_draws": 0,
          "coverage_status": "under_covered",
          "distinct_rated_opponents": 9,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "minimal",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "qwen/qwen3.8-max",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 0,
          "model": "qwen/qwen3.8-max",
          "point_rating_method": "sequential_elo",
          "public_id": "E-776235fa35035a89",
          "rated_matches": 17,
          "raw_elo_rating": 1725.7042357575813,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "minimal",
          "repair_status": "first_pass",
          "score": 61.919231042616644,
          "uncertainty": 74.10113019775793,
          "unilateral_faults": 0,
          "wins": 17
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 22,
          "capped_draws": 0,
          "coverage_status": "under_covered",
          "distinct_rated_opponents": 11,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "xhigh",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "qwen/qwen3.8-max",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 9,
          "model": "qwen/qwen3.8-max",
          "point_rating_method": "sequential_elo",
          "public_id": "E-7cc7204834cbed5f",
          "rated_matches": 22,
          "raw_elo_rating": 1528.9563415565945,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "xhigh",
          "repair_status": "first_pass",
          "score": 46.48436747017905,
          "uncertainty": 60.5072070285374,
          "unilateral_faults": 0,
          "wins": 13
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 16,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 8,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "low",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "stealth/ox-alpha",
            "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-08-22T00:27:26Z",
          "losses": 9,
          "model": "stealth/ox-alpha",
          "point_rating_method": "sequential_elo",
          "public_id": "E-070bbd8b3ce0460a",
          "rated_matches": 16,
          "raw_elo_rating": 1460.5264281995208,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "low",
          "repair_status": "repaired",
          "score": 39.67190336042129,
          "uncertainty": 77.5178125181665,
          "unilateral_faults": 0,
          "wins": 7
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 16,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 8,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "stealth/ox-alpha",
            "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-08-22T00:27:26Z",
          "losses": 10,
          "model": "stealth/ox-alpha",
          "point_rating_method": "sequential_elo",
          "public_id": "E-149dc099de9a50cd",
          "rated_matches": 16,
          "raw_elo_rating": 1449.6235991611914,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "first_pass",
          "score": 38.76653302705747,
          "uncertainty": 77.5178125181665,
          "unilateral_faults": 0,
          "wins": 6
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 16,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 8,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "max",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "stealth/ox-alpha",
            "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-08-22T00:27:26Z",
          "losses": 6,
          "model": "stealth/ox-alpha",
          "point_rating_method": "sequential_elo",
          "public_id": "E-45b32dc2eea8fd55",
          "rated_matches": 16,
          "raw_elo_rating": 1550.9689443760603,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "max",
          "repair_status": "first_pass",
          "score": 47.18224500965281,
          "uncertainty": 77.5178125181665,
          "unilateral_faults": 0,
          "wins": 10
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 16,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 8,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "low",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "stealth/ox-alpha",
            "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-08-22T00:27:26Z",
          "losses": 7,
          "model": "stealth/ox-alpha",
          "point_rating_method": "sequential_elo",
          "public_id": "E-575e460fdd8ace42",
          "rated_matches": 16,
          "raw_elo_rating": 1513.161649921587,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "low",
          "repair_status": "first_pass",
          "score": 44.042729323999595,
          "uncertainty": 77.5178125181665,
          "unilateral_faults": 0,
          "wins": 9
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 16,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 8,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "stealth/ox-alpha",
            "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-08-22T00:27:26Z",
          "losses": 16,
          "model": "stealth/ox-alpha",
          "point_rating_method": "sequential_elo",
          "public_id": "E-6f88d9900795b3a1",
          "rated_matches": 16,
          "raw_elo_rating": 1318.0835583843711,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "first_pass",
          "score": 27.843455158907382,
          "uncertainty": 77.5178125181665,
          "unilateral_faults": 0,
          "wins": 0
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 16,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 8,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "stealth/ox-alpha",
            "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-08-22T00:27:26Z",
          "losses": 8,
          "model": "stealth/ox-alpha",
          "point_rating_method": "sequential_elo",
          "public_id": "E-71c7a6b241c3e968",
          "rated_matches": 16,
          "raw_elo_rating": 1512.5352198384758,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "first_pass",
          "score": 43.99071060379572,
          "uncertainty": 77.5178125181665,
          "unilateral_faults": 0,
          "wins": 8
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 16,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 8,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "max",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "stealth/ox-alpha",
            "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-08-22T00:27:26Z",
          "losses": 7,
          "model": "stealth/ox-alpha",
          "point_rating_method": "sequential_elo",
          "public_id": "E-b2ff4a9d0e899fba",
          "rated_matches": 16,
          "raw_elo_rating": 1528.592744862467,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "max",
          "repair_status": "first_pass",
          "score": 45.324126612875546,
          "uncertainty": 77.5178125181665,
          "unilateral_faults": 0,
          "wins": 9
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 16,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 8,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "max",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "stealth/ox-alpha",
            "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-08-22T00:27:26Z",
          "losses": 2,
          "model": "stealth/ox-alpha",
          "point_rating_method": "sequential_elo",
          "public_id": "E-b6ae2b718b132aa0",
          "rated_matches": 16,
          "raw_elo_rating": 1634.7728591293924,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "max",
          "repair_status": "repaired",
          "score": 54.14131755593233,
          "uncertainty": 77.5178125181665,
          "unilateral_faults": 0,
          "wins": 14
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 16,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 8,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "low",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "stealth/ox-alpha",
            "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-08-22T00:27:26Z",
          "losses": 7,
          "model": "stealth/ox-alpha",
          "point_rating_method": "sequential_elo",
          "public_id": "E-c69bc9b31ddf984b",
          "rated_matches": 16,
          "raw_elo_rating": 1531.7349961269342,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "low",
          "repair_status": "first_pass",
          "score": 45.585058987841904,
          "uncertainty": 77.5178125181665,
          "unilateral_faults": 0,
          "wins": 9
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 108,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 52,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "stepfun/step-3.7-flash",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 52,
          "model": "stepfun/step-3.7-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-358338a9fbdbcb6a",
          "rated_matches": 108,
          "raw_elo_rating": 1425.1003871142666,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "repaired",
          "score": 41.604671181441674,
          "uncertainty": 4.1413142610575715,
          "unilateral_faults": 0,
          "wins": 56
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 154,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 56,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "low",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "stepfun/step-3.7-flash",
            "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-21T14:20:15Z",
          "losses": 99,
          "model": "stepfun/step-3.7-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-50f22f1c15a8fd4a",
          "rated_matches": 150,
          "raw_elo_rating": 1299.4636047831602,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "low",
          "repair_status": "first_pass",
          "score": 31.650235307750318,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 51
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 118,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 58,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "stepfun/step-3.7-flash",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 66,
          "model": "stepfun/step-3.7-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-7b9b33921ba865f5",
          "rated_matches": 118,
          "raw_elo_rating": 1491.530653934251,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "repaired",
          "score": 47.2576469157077,
          "uncertainty": 2.084924851410568,
          "unilateral_faults": 0,
          "wins": 52
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 104,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 52,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "tencent/hy3-preview",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 63,
          "model": "tencent/hy3-preview",
          "point_rating_method": "sequential_elo",
          "public_id": "E-1bb81f8a4ae78954",
          "rated_matches": 104,
          "raw_elo_rating": 1329.3883779909766,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 33.59671726886273,
          "uncertainty": 5.045003647426665,
          "unilateral_faults": 0,
          "wins": 41
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 96,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 46,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "tencent/hy3-preview",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-03T19:10:00Z",
          "losses": 48,
          "model": "tencent/hy3-preview",
          "point_rating_method": "sequential_elo",
          "public_id": "E-92dc0ac61d798488",
          "rated_matches": 96,
          "raw_elo_rating": 1628.3276946126373,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "repaired",
          "score": 58.289597890358415,
          "uncertainty": 7.017308256680951,
          "unilateral_faults": 0,
          "wins": 48
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 104,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 52,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "thinkingmachines/inkling",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 69,
          "model": "thinkingmachines/inkling",
          "point_rating_method": "sequential_elo",
          "public_id": "E-0f05573125dedc2b",
          "rated_matches": 104,
          "raw_elo_rating": 1292.1576760716523,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "repaired",
          "score": 30.505081796127445,
          "uncertainty": 5.045003647426665,
          "unilateral_faults": 0,
          "wins": 35
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 154,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 53,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "max",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "thinkingmachines/inkling",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 126,
          "model": "thinkingmachines/inkling",
          "point_rating_method": "sequential_elo",
          "public_id": "E-2c483dc32fc18ba8",
          "rated_matches": 154,
          "raw_elo_rating": 1095.9127049060485,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "max",
          "repair_status": "first_pass",
          "score": 14.782485995492653,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 28
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 124,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 62,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "thinkingmachines/inkling",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 80,
          "model": "thinkingmachines/inkling",
          "point_rating_method": "sequential_elo",
          "public_id": "E-ae60ed096a69eeff",
          "rated_matches": 124,
          "raw_elo_rating": 1241.8551704733636,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "repaired",
          "score": 26.598584601571144,
          "uncertainty": 0.9713595499957961,
          "unilateral_faults": 0,
          "wins": 44
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 166,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 59,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "max",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "thinkingmachines/inkling",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 124,
          "model": "thinkingmachines/inkling",
          "point_rating_method": "sequential_elo",
          "public_id": "E-e9202aa1565d1c4e",
          "rated_matches": 166,
          "raw_elo_rating": 1183.8805167121868,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "max",
          "repair_status": "repaired",
          "score": 22.184970337787764,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 42
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 110,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 55,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "thinkingmachines/inkling",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 73,
          "model": "thinkingmachines/inkling",
          "point_rating_method": "sequential_elo",
          "public_id": "E-f7a1d86c7e241f8d",
          "rated_matches": 110,
          "raw_elo_rating": 1305.539750894517,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 31.70515499101209,
          "uncertainty": 3.707899787624953,
          "unilateral_faults": 0,
          "wins": 37
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 18,
          "capped_draws": 0,
          "coverage_status": "under_covered",
          "distinct_rated_opponents": 7,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "thinkingmachines/inkling-small",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 17,
          "model": "thinkingmachines/inkling-small",
          "point_rating_method": "sequential_elo",
          "public_id": "E-7c80d62319ac1a53",
          "rated_matches": 18,
          "raw_elo_rating": 1275.2637241074317,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 24.72348845861986,
          "uncertainty": 70.95786693528086,
          "unilateral_faults": 0,
          "wins": 1
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 16,
          "capped_draws": 0,
          "coverage_status": "under_covered",
          "distinct_rated_opponents": 8,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "thinkingmachines/inkling-small",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 12,
          "model": "thinkingmachines/inkling-small",
          "point_rating_method": "sequential_elo",
          "public_id": "E-cb36e2fcb99cfafd",
          "rated_matches": 16,
          "raw_elo_rating": 1363.5335221414252,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 31.61761768988316,
          "uncertainty": 77.5178125181665,
          "unilateral_faults": 0,
          "wins": 4
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 17,
          "capped_draws": 0,
          "coverage_status": "under_covered",
          "distinct_rated_opponents": 9,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "max",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "thinkingmachines/inkling-small",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 8,
          "model": "thinkingmachines/inkling-small",
          "point_rating_method": "sequential_elo",
          "public_id": "E-e8805bb60afd625c",
          "rated_matches": 17,
          "raw_elo_rating": 1503.5327853795927,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "max",
          "repair_status": "first_pass",
          "score": 43.47012582547535,
          "uncertainty": 74.10113019775793,
          "unilateral_faults": 0,
          "wins": 9
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 161,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 65,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "low",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "x-ai/grok-4.5",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T14:00:00Z",
          "losses": 85,
          "model": "x-ai/grok-4.5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-3c5879def34f7d38",
          "rated_matches": 161,
          "raw_elo_rating": 1474.9702034985373,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "low",
          "repair_status": "first_pass",
          "score": 46.31767802468079,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 76
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 116,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 58,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "x-ai/grok-4.5",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T14:00:00Z",
          "losses": 46,
          "model": "x-ai/grok-4.5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-824ec3caceabd338",
          "rated_matches": 116,
          "raw_elo_rating": 1660.642134309636,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 61.274740553352146,
          "uncertainty": 2.4750163521024238,
          "unilateral_faults": 0,
          "wins": 70
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 142,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 56,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "x-ai/grok-4.5",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T14:00:00Z",
          "losses": 41,
          "model": "x-ai/grok-4.5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-8e6cb252293b2af9",
          "rated_matches": 142,
          "raw_elo_rating": 1780.9418496208198,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "first_pass",
          "score": 71.55758103790589,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 101
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 124,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 57,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "enabled",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "x-ai/grok-build-0.1",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 60,
          "model": "x-ai/grok-build-0.1",
          "point_rating_method": "sequential_elo",
          "public_id": "E-4aac1b6621aeae38",
          "rated_matches": 124,
          "raw_elo_rating": 1685.2701621628198,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "enabled",
          "repair_status": "repaired",
          "score": 63.41974151718129,
          "uncertainty": 0.9713595499957961,
          "unilateral_faults": 0,
          "wins": 64
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 86,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 43,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "xiaomi/mimo-v2.5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 34,
          "model": "xiaomi/mimo-v2.5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-09d406abc15f7c9a",
          "rated_matches": 86,
          "raw_elo_rating": 1643.2983032623679,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 59.344201371796736,
          "uncertainty": 9.855626741889738,
          "unilateral_faults": 0,
          "wins": 52
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 86,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 43,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "xiaomi/mimo-v2.5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-01T00:15:48Z",
          "losses": 54,
          "model": "xiaomi/mimo-v2.5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-9490f08c56c27d13",
          "rated_matches": 86,
          "raw_elo_rating": 1295.9502483176454,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "repaired",
          "score": 30.500437685049647,
          "uncertainty": 9.855626741889738,
          "unilateral_faults": 0,
          "wins": 32
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 130,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 63,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "enabled",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "xiaomi/mimo-v2.5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 67,
          "model": "xiaomi/mimo-v2.5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-ad48cf51fe7da3cc",
          "rated_matches": 130,
          "raw_elo_rating": 1446.9669001608218,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "enabled",
          "repair_status": "repaired",
          "score": 43.69988545387929,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 63
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 84,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 42,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "xiaomi/mimo-v2.5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T06:10:40Z",
          "losses": 45,
          "model": "xiaomi/mimo-v2.5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-be8fc9653466bbe1",
          "rated_matches": 84,
          "raw_elo_rating": 1375.0951588392095,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 37.03097475144065,
          "uncertainty": 10.482614454664043,
          "unilateral_faults": 0,
          "wins": 39
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 114,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 57,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "xiaomi/mimo-v2.5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T06:10:40Z",
          "losses": 73,
          "model": "xiaomi/mimo-v2.5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-faaa866ee28d6401",
          "rated_matches": 114,
          "raw_elo_rating": 1384.689357216663,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "repaired",
          "score": 38.33304920861673,
          "uncertainty": 2.875240412015687,
          "unilateral_faults": 0,
          "wins": 41
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 110,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 53,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "enabled",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "xiaomi/mimo-v2.5-pro",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 71,
          "model": "xiaomi/mimo-v2.5-pro",
          "point_rating_method": "sequential_elo",
          "public_id": "E-9c228ad72a159b33",
          "rated_matches": 110,
          "raw_elo_rating": 1293.3384425319216,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "enabled",
          "repair_status": "repaired",
          "score": 30.691959004825147,
          "uncertainty": 3.707899787624953,
          "unilateral_faults": 0,
          "wins": 39
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 98,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 49,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "xiaomi/mimo-v2.5-pro",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 46,
          "model": "xiaomi/mimo-v2.5-pro",
          "point_rating_method": "sequential_elo",
          "public_id": "E-af55f57b03605914",
          "rated_matches": 98,
          "raw_elo_rating": 1444.8486850159818,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 43.08775105458573,
          "uncertainty": 6.501890762960602,
          "unilateral_faults": 0,
          "wins": 52
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 84,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 42,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "z-ai/glm-5.2",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-11T14:00:45Z",
          "losses": 40,
          "model": "z-ai/glm-5.2",
          "point_rating_method": "sequential_elo",
          "public_id": "E-38e323f4ce233fa1",
          "rated_matches": 84,
          "raw_elo_rating": 1403.656288266575,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 39.40268939357571,
          "uncertainty": 10.482614454664043,
          "unilateral_faults": 0,
          "wins": 44
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 84,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 42,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "z-ai/glm-5.2",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-11T17:22:09Z",
          "losses": 42,
          "model": "z-ai/glm-5.2",
          "point_rating_method": "sequential_elo",
          "public_id": "E-3916ba303b2ff700",
          "rated_matches": 84,
          "raw_elo_rating": 1563.1378187943271,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "repaired",
          "score": 52.64602705866004,
          "uncertainty": 10.482614454664043,
          "unilateral_faults": 0,
          "wins": 42
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 82,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 41,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "z-ai/glm-5.2",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 42,
          "model": "z-ai/glm-5.2",
          "point_rating_method": "sequential_elo",
          "public_id": "E-d8655d29a4806df8",
          "rated_matches": 82,
          "raw_elo_rating": 1632.583520626269,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "repaired",
          "score": 58.369645792657955,
          "uncertainty": 11.132129994845172,
          "unilateral_faults": 0,
          "wins": 40
        }
      ],
      "GB2-06": [
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 84,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 39,
          "draws": 9,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "xhigh",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-fable-5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 10,
          "model": "claude-fable-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-499fbc92ee0778fb",
          "rated_matches": 84,
          "raw_elo_rating": 1909.8483590250705,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "xhigh",
          "repair_status": "repaired",
          "score": 84.82657150590221,
          "uncertainty": 10.482614454664043,
          "unilateral_faults": 0,
          "wins": 65
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 92,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 45,
          "draws": 5,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-fable-5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 22,
          "model": "claude-fable-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-e1ca3ac536f3eb1e",
          "rated_matches": 92,
          "raw_elo_rating": 1815.5838157198623,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 76.8393903737067,
          "uncertainty": 8.09758473652126,
          "unilateral_faults": 0,
          "wins": 65
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 196,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 71,
          "draws": 16,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-opus-4-5",
            "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 82,
          "model": "claude-opus-4-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-1ff6d6f973c7157d",
          "rated_matches": 196,
          "raw_elo_rating": 1500.9782452617544,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 50.754127680852754,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 98
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 96,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 48,
          "draws": 5,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-opus-4-5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "omitted",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 44,
          "model": "claude-opus-4-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-40a259ca8a40b5b4",
          "rated_matches": 96,
          "raw_elo_rating": 1433.511289483019,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "omitted",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 43.871714707416494,
          "uncertainty": 7.017308256680951,
          "unilateral_faults": 0,
          "wins": 47
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 0,
          "capped_draws": 0,
          "coverage_status": "pending",
          "distinct_rated_opponents": 0,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "legacy_shared_thinking_budget",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-opus-4-5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "budget",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 0,
          "model": "claude-opus-4-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-41f8f2b491917557",
          "rated_matches": 0,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "budget",
          "reasoning_setting": "legacy_shared_thinking_budget",
          "repair_status": "repaired",
          "unilateral_faults": 0,
          "wins": 0
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 0,
          "capped_draws": 0,
          "coverage_status": "pending",
          "distinct_rated_opponents": 0,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "legacy_shared_thinking_budget",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-opus-4-5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "budget",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 0,
          "model": "claude-opus-4-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-8e040f66441f7747",
          "rated_matches": 0,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "budget",
          "reasoning_setting": "legacy_shared_thinking_budget",
          "repair_status": "first_pass",
          "unilateral_faults": 0,
          "wins": 0
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 178,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 64,
          "draws": 17,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-opus-4-5",
            "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 71,
          "model": "claude-opus-4-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-df9bde92610963b7",
          "rated_matches": 178,
          "raw_elo_rating": 1601.6726322378718,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "first_pass",
          "score": 59.34143229501704,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 90
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 92,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 46,
          "draws": 1,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-opus-4-8",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 22,
          "model": "claude-opus-4-8",
          "point_rating_method": "sequential_elo",
          "public_id": "E-39e283268f14261d",
          "rated_matches": 92,
          "raw_elo_rating": 1799.7073501929144,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 75.46636108950283,
          "uncertainty": 8.09758473652126,
          "unilateral_faults": 0,
          "wins": 69
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 90,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 45,
          "draws": 9,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-opus-4-8",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "omitted",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 30,
          "model": "claude-opus-4-8",
          "point_rating_method": "sequential_elo",
          "public_id": "E-db414178442322d3",
          "rated_matches": 90,
          "raw_elo_rating": 1559.4794101376715,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "omitted",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 54.6517518521781,
          "uncertainty": 8.664241836095918,
          "unilateral_faults": 0,
          "wins": 51
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 84,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 38,
          "draws": 2,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "xhigh",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-opus-4-8",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-03T17:20:00Z",
          "losses": 18,
          "model": "claude-opus-4-8",
          "point_rating_method": "sequential_elo",
          "public_id": "E-e804041031295d93",
          "rated_matches": 84,
          "raw_elo_rating": 1827.373724966149,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "xhigh",
          "repair_status": "first_pass",
          "score": 77.69399608634865,
          "uncertainty": 10.482614454664043,
          "unilateral_faults": 0,
          "wins": 64
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 104,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 52,
          "draws": 11,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-opus-5",
            "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-25T10:50:00Z",
          "losses": 5,
          "model": "claude-opus-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-ca8985adf5006428",
          "rated_matches": 104,
          "raw_elo_rating": 1978.901816863329,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 91.17466067700593,
          "uncertainty": 5.045003647426665,
          "unilateral_faults": 0,
          "wins": 88
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 120,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 59,
          "draws": 4,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-sonnet-5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 54,
          "model": "claude-sonnet-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-01597b81edc004dd",
          "rated_matches": 120,
          "raw_elo_rating": 1443.2412427006718,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 45.08074790155403,
          "uncertainty": 1.7045454545454586,
          "unilateral_faults": 0,
          "wins": 62
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 86,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 43,
          "draws": 3,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-sonnet-5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 39,
          "model": "claude-sonnet-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-500304c7462c6005",
          "rated_matches": 86,
          "raw_elo_rating": 1575.5939478505748,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 55.96294337993718,
          "uncertainty": 9.855626741889738,
          "unilateral_faults": 0,
          "wins": 44
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 96,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 45,
          "draws": 11,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "xhigh",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-sonnet-5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-03T16:50:00Z",
          "losses": 35,
          "model": "claude-sonnet-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-51f3682dc3b76107",
          "rated_matches": 96,
          "raw_elo_rating": 1630.987339864078,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "xhigh",
          "repair_status": "first_pass",
          "score": 60.949848353843976,
          "uncertainty": 7.017308256680951,
          "unilateral_faults": 0,
          "wins": 50
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 94,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 43,
          "draws": 4,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-sonnet-5",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 45,
          "model": "claude-sonnet-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-63360bf4842cdf18",
          "rated_matches": 94,
          "raw_elo_rating": 1493.6367483030979,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 49.03470790545843,
          "uncertainty": 7.54891760425771,
          "unilateral_faults": 0,
          "wins": 45
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 92,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 42,
          "draws": 5,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "xhigh",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-sonnet-5",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 64,
          "model": "claude-sonnet-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-c4133ea4f4d4dfb9",
          "rated_matches": 92,
          "raw_elo_rating": 1282.520215691405,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "xhigh",
          "repair_status": "first_pass",
          "score": 30.738957507215925,
          "uncertainty": 8.09758473652126,
          "unilateral_faults": 0,
          "wins": 23
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 94,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 44,
          "draws": 3,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-sonnet-5",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 58,
          "model": "claude-sonnet-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-fa6cc450ec345534",
          "rated_matches": 94,
          "raw_elo_rating": 1429.842052186386,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 43.517611811465784,
          "uncertainty": 7.54891760425771,
          "unilateral_faults": 0,
          "wins": 33
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 70,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 35,
          "draws": 1,
          "evaluated_setting_identity": {
            "canonical_provider_route": "unknown_legacy",
            "effective_request_value": "enabled",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "cohere/north-mini-code:free",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 55,
          "model": "cohere/north-mini-code",
          "point_rating_method": "sequential_elo",
          "public_id": "E-78dfcb6ce8b3efaa",
          "rated_matches": 70,
          "raw_elo_rating": 1246.4470947825891,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "enabled",
          "repair_status": "first_pass",
          "score": 27.100975968953843,
          "uncertainty": 15.58908290969266,
          "unilateral_faults": 0,
          "wins": 14
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 86,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 40,
          "draws": 1,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "xhigh",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "deepseek/deepseek-v4-flash",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 61,
          "model": "deepseek/deepseek-v4-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-5f5fd61f4544b8d7",
          "rated_matches": 86,
          "raw_elo_rating": 1269.9135910657938,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "xhigh",
          "repair_status": "first_pass",
          "score": 29.52707950589016,
          "uncertainty": 9.855626741889738,
          "unilateral_faults": 0,
          "wins": 24
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 80,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 40,
          "draws": 1,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "deepseek/deepseek-v4-flash",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T06:10:40Z",
          "losses": 41,
          "model": "deepseek/deepseek-v4-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-6f20412107151172",
          "rated_matches": 80,
          "raw_elo_rating": 1344.5151990016536,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 35.8438724144747,
          "uncertainty": 11.805555555555554,
          "unilateral_faults": 0,
          "wins": 38
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 80,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 40,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "deepseek/deepseek-v4-flash",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-01T00:15:48Z",
          "losses": 60,
          "model": "deepseek/deepseek-v4-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-d8ca2fcf88af96c7",
          "rated_matches": 80,
          "raw_elo_rating": 1144.0113215973251,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "repaired",
          "score": 18.503886080281386,
          "uncertainty": 11.805555555555554,
          "unilateral_faults": 0,
          "wins": 20
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 90,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 44,
          "draws": 1,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "deepseek/deepseek-v4-flash",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 70,
          "model": "deepseek/deepseek-v4-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-db0efb02339d9e80",
          "rated_matches": 90,
          "raw_elo_rating": 1123.1640710825773,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 16.918306920549412,
          "uncertainty": 8.664241836095918,
          "unilateral_faults": 0,
          "wins": 19
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 86,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 43,
          "draws": 8,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "deepseek/deepseek-v4-pro",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 24,
          "model": "deepseek/deepseek-v4-pro",
          "point_rating_method": "sequential_elo",
          "public_id": "E-945bebaa34963e03",
          "rated_matches": 86,
          "raw_elo_rating": 1670.4616001827212,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 64.1672924244156,
          "uncertainty": 9.855626741889738,
          "unilateral_faults": 0,
          "wins": 54
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 118,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 58,
          "draws": 2,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "xhigh",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "deepseek/deepseek-v4-pro",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 63,
          "model": "deepseek/deepseek-v4-pro",
          "point_rating_method": "sequential_elo",
          "public_id": "E-c9778645f1bbd12c",
          "rated_matches": 118,
          "raw_elo_rating": 1399.9603695080434,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "xhigh",
          "repair_status": "first_pass",
          "score": 41.31141247367678,
          "uncertainty": 2.084924851410568,
          "unilateral_faults": 0,
          "wins": 53
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 95,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 45,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "google/gemini-3.1-flash-lite",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 66,
          "model": "google/gemini-3.1-flash-lite",
          "point_rating_method": "sequential_elo",
          "public_id": "E-6238c7d8dc9e77d9",
          "rated_matches": 95,
          "raw_elo_rating": 1265.0077154404437,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "repaired",
          "score": 29.280934011909366,
          "uncertainty": 7.281036307982882,
          "unilateral_faults": 0,
          "wins": 29
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 132,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 66,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "google/gemini-3.1-flash-lite",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 82,
          "model": "google/gemini-3.1-flash-lite",
          "point_rating_method": "sequential_elo",
          "public_id": "E-a10101fbca309818",
          "rated_matches": 132,
          "raw_elo_rating": 1399.0006395624505,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 41.39995376105174,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 50
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 80,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 40,
          "draws": 1,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "google/gemini-3.1-flash-lite",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 36,
          "model": "google/gemini-3.1-flash-lite",
          "point_rating_method": "sequential_elo",
          "public_id": "E-dc1c0f46738d1091",
          "rated_matches": 80,
          "raw_elo_rating": 1381.2364236832755,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 39.0195992003968,
          "uncertainty": 11.805555555555554,
          "unilateral_faults": 0,
          "wins": 43
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 86,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 43,
          "draws": 11,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "google/gemini-3.5-flash",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 12,
          "model": "google/gemini-3.5-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-35d6e87056063577",
          "rated_matches": 86,
          "raw_elo_rating": 1868.3321704609657,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "repaired",
          "score": 81.27954496028467,
          "uncertainty": 9.855626741889738,
          "unilateral_faults": 0,
          "wins": 63
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 84,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 40,
          "draws": 5,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "google/gemini-3.5-flash",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 17,
          "model": "google/gemini-3.5-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-5dcb27eaa0273049",
          "rated_matches": 84,
          "raw_elo_rating": 1877.810620435143,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "repaired",
          "score": 82.05588219794666,
          "uncertainty": 10.482614454664043,
          "unilateral_faults": 0,
          "wins": 62
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 0,
          "capped_draws": 0,
          "coverage_status": "pending",
          "distinct_rated_opponents": 0,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "low",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "google/gemini-3.5-flash",
            "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-21T14:20:15Z",
          "losses": 0,
          "model": "google/gemini-3.5-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-8d5209853815321d",
          "rated_matches": 0,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "low",
          "repair_status": "first_pass",
          "unilateral_faults": 0,
          "wins": 0
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 144,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 51,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "google/gemini-3.5-flash-lite",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 108,
          "model": "google/gemini-3.5-flash-lite",
          "point_rating_method": "sequential_elo",
          "public_id": "E-09a450a1726f909a",
          "rated_matches": 144,
          "raw_elo_rating": 1152.7930953344032,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "first_pass",
          "score": 20.234221204308028,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 36
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 158,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 60,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "google/gemini-3.5-flash-lite",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 136,
          "model": "google/gemini-3.5-flash-lite",
          "point_rating_method": "sequential_elo",
          "public_id": "E-3d6c386b0f48e1c1",
          "rated_matches": 158,
          "raw_elo_rating": 1111.4329647963032,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 16.786700591269984,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 22
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 150,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 55,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "minimal",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "google/gemini-3.5-flash-lite",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 66,
          "model": "google/gemini-3.5-flash-lite",
          "point_rating_method": "sequential_elo",
          "public_id": "E-3efea50fdbbd1829",
          "rated_matches": 150,
          "raw_elo_rating": 1576.4149483402527,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "minimal",
          "repair_status": "first_pass",
          "score": 56.92756101091148,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 84
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 152,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 58,
          "draws": 4,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "minimal",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "google/gemini-3.5-flash-lite",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 50,
          "model": "google/gemini-3.5-flash-lite",
          "point_rating_method": "sequential_elo",
          "public_id": "E-46f1468c28505bfe",
          "rated_matches": 152,
          "raw_elo_rating": 1664.3918949877018,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "minimal",
          "repair_status": "repaired",
          "score": 64.55444772946453,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 98
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 150,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 55,
          "draws": 13,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "google/gemini-3.5-flash-lite",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 44,
          "model": "google/gemini-3.5-flash-lite",
          "point_rating_method": "sequential_elo",
          "public_id": "E-48cc2611d5aa8816",
          "rated_matches": 150,
          "raw_elo_rating": 1719.306434738836,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "repaired",
          "score": 69.28510967031967,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 93
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 158,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 60,
          "draws": 4,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "google/gemini-3.5-flash-lite",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 124,
          "model": "google/gemini-3.5-flash-lite",
          "point_rating_method": "sequential_elo",
          "public_id": "E-892a28a528dad9c8",
          "rated_matches": 158,
          "raw_elo_rating": 1178.6148740470483,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 22.596729820598927,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 30
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 164,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 66,
          "draws": 12,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "google/gemini-3.6-flash",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 35,
          "model": "google/gemini-3.6-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-280a7de63c992141",
          "rated_matches": 164,
          "raw_elo_rating": 1864.479412642781,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "repaired",
          "score": 81.96204277453973,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 117
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 154,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 60,
          "draws": 11,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "google/gemini-3.6-flash",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 13,
          "model": "google/gemini-3.6-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-33485e8cce3184c3",
          "rated_matches": 154,
          "raw_elo_rating": 1936.0392948227586,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 88.0651732953837,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 130
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 168,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 60,
          "draws": 33,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "minimal",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "google/gemini-3.6-flash",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 89,
          "model": "google/gemini-3.6-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-5455742d003ec402",
          "rated_matches": 168,
          "raw_elo_rating": 1366.054909970448,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "minimal",
          "repair_status": "repaired",
          "score": 38.8893312853542,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 46
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 150,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 58,
          "draws": 2,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "google/gemini-3.6-flash",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 11,
          "model": "google/gemini-3.6-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-905531e52a8460f5",
          "rated_matches": 150,
          "raw_elo_rating": 2074.465573071347,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "repaired",
          "score": 100.0,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 137
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 161,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 58,
          "draws": 2,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "minimal",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "google/gemini-3.6-flash",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 123,
          "model": "google/gemini-3.6-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-bb2e288b40b1a588",
          "rated_matches": 161,
          "raw_elo_rating": 1143.9370062291084,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "minimal",
          "repair_status": "first_pass",
          "score": 19.62323717799623,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 36
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 154,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 61,
          "draws": 10,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "google/gemini-3.6-flash",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 8,
          "model": "google/gemini-3.6-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-bdf020e4fa85b365",
          "rated_matches": 154,
          "raw_elo_rating": 1977.7578215531246,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 91.67307700653463,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 136
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 118,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 58,
          "draws": 1,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "enabled",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "google/gemma-4-31b-it",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 76,
          "model": "google/gemma-4-31b-it",
          "point_rating_method": "sequential_elo",
          "public_id": "E-41987f96551bf9d3",
          "rated_matches": 118,
          "raw_elo_rating": 1333.1575713568993,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "enabled",
          "repair_status": "repaired",
          "score": 35.53416954938754,
          "uncertainty": 2.084924851410568,
          "unilateral_faults": 0,
          "wins": 41
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 102,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 49,
          "draws": 2,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "google/gemma-4-31b-it",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 59,
          "model": "google/gemma-4-31b-it",
          "point_rating_method": "sequential_elo",
          "public_id": "E-da266f7bbd330107",
          "rated_matches": 102,
          "raw_elo_rating": 1313.9232512674864,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 33.633332893697606,
          "uncertainty": 5.516463908214657,
          "unilateral_faults": 0,
          "wins": 41
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 92,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 46,
          "draws": 10,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-4.1",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "omitted",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 35,
          "model": "gpt-4.1",
          "point_rating_method": "sequential_elo",
          "public_id": "E-4dcd6d3653c67437",
          "rated_matches": 92,
          "raw_elo_rating": 1555.174459690298,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "omitted",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 54.318655446755876,
          "uncertainty": 8.09758473652126,
          "unilateral_faults": 0,
          "wins": 47
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 90,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 42,
          "draws": 9,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 31,
          "model": "gpt-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-1b082700b3692175",
          "rated_matches": 90,
          "raw_elo_rating": 1690.7719660077682,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "repaired",
          "score": 66.00620122264021,
          "uncertainty": 8.664241836095918,
          "unilateral_faults": 0,
          "wins": 50
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 104,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 51,
          "draws": 7,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 42,
          "model": "gpt-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-816d262cd933cdb9",
          "rated_matches": 104,
          "raw_elo_rating": 1580.3019624316037,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 56.70292816921177,
          "uncertainty": 5.045003647426665,
          "unilateral_faults": 0,
          "wins": 55
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 84,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 42,
          "draws": 9,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.4",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 22,
          "model": "gpt-5.4",
          "point_rating_method": "sequential_elo",
          "public_id": "E-00a57c19a4229948",
          "rated_matches": 84,
          "raw_elo_rating": 1716.938756792082,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 68.14335365615862,
          "uncertainty": 10.482614454664043,
          "unilateral_faults": 0,
          "wins": 53
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 96,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 43,
          "draws": 3,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "xhigh",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.4",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 6,
          "model": "gpt-5.4",
          "point_rating_method": "sequential_elo",
          "public_id": "E-5032a25edce1eb13",
          "rated_matches": 96,
          "raw_elo_rating": 1948.9952096118298,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "xhigh",
          "repair_status": "first_pass",
          "score": 88.45182081930464,
          "uncertainty": 7.017308256680951,
          "unilateral_faults": 0,
          "wins": 87
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 82,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 41,
          "draws": 9,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.4",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 5,
          "model": "gpt-5.4",
          "point_rating_method": "sequential_elo",
          "public_id": "E-61f3ed920d3c145d",
          "rated_matches": 82,
          "raw_elo_rating": 1911.8869424079114,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "repaired",
          "score": 84.95793522748247,
          "uncertainty": 11.132129994845172,
          "unilateral_faults": 0,
          "wins": 68
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 84,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 39,
          "draws": 10,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "xhigh",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.4",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 7,
          "model": "gpt-5.4",
          "point_rating_method": "sequential_elo",
          "public_id": "E-6e5bbab022d4d9fa",
          "rated_matches": 84,
          "raw_elo_rating": 1963.0028481780307,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "xhigh",
          "repair_status": "repaired",
          "score": 89.42348069013059,
          "uncertainty": 10.482614454664043,
          "unilateral_faults": 0,
          "wins": 67
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 92,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 42,
          "draws": 3,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.4",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 8,
          "model": "gpt-5.4",
          "point_rating_method": "sequential_elo",
          "public_id": "E-cbb31028768b544a",
          "rated_matches": 92,
          "raw_elo_rating": 1886.7419988126178,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 82.99329591592327,
          "uncertainty": 8.09758473652126,
          "unilateral_faults": 0,
          "wins": 81
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 96,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 43,
          "draws": 4,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.4",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 18,
          "model": "gpt-5.4",
          "point_rating_method": "sequential_elo",
          "public_id": "E-eb2b19ed78a802af",
          "rated_matches": 96,
          "raw_elo_rating": 1780.420554955911,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "repaired",
          "score": 73.87313912064397,
          "uncertainty": 7.017308256680951,
          "unilateral_faults": 0,
          "wins": 74
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 98,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 47,
          "draws": 6,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.4-mini",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 46,
          "model": "gpt-5.4-mini",
          "point_rating_method": "sequential_elo",
          "public_id": "E-144154b792c9e9a6",
          "rated_matches": 98,
          "raw_elo_rating": 1335.615860264783,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "repaired",
          "score": 35.44117680027425,
          "uncertainty": 6.501890762960602,
          "unilateral_faults": 0,
          "wins": 46
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 108,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 54,
          "draws": 12,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.4-mini",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 43,
          "model": "gpt-5.4-mini",
          "point_rating_method": "sequential_elo",
          "public_id": "E-3ccfe46cbdc271eb",
          "rated_matches": 108,
          "raw_elo_rating": 1559.2793243998406,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 54.94736966606298,
          "uncertainty": 4.1413142610575715,
          "unilateral_faults": 0,
          "wins": 53
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 110,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 55,
          "draws": 3,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.4-nano",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 47,
          "model": "gpt-5.4-nano",
          "point_rating_method": "sequential_elo",
          "public_id": "E-5ccde5c853d97bd9",
          "rated_matches": 110,
          "raw_elo_rating": 1687.0433490489509,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "repaired",
          "score": 66.02665048103961,
          "uncertainty": 3.707899787624953,
          "unilateral_faults": 0,
          "wins": 60
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 104,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 51,
          "draws": 3,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.4-nano",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-09T17:30:50Z",
          "losses": 39,
          "model": "gpt-5.4-nano",
          "point_rating_method": "sequential_elo",
          "public_id": "E-9c5263dcfd4c2ec7",
          "rated_matches": 104,
          "raw_elo_rating": 1581.248219683735,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 56.78476243612473,
          "uncertainty": 5.045003647426665,
          "unilateral_faults": 0,
          "wins": 62
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 100,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 48,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.4-nano",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-09T17:30:50Z",
          "losses": 55,
          "model": "gpt-5.4-nano",
          "point_rating_method": "sequential_elo",
          "public_id": "E-a1fb59d78d39d217",
          "rated_matches": 100,
          "raw_elo_rating": 1355.8723491350454,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 37.22759446407967,
          "uncertainty": 6.001859510499461,
          "unilateral_faults": 0,
          "wins": 45
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 96,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 48,
          "draws": 1,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.4-nano",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 31,
          "model": "gpt-5.4-nano",
          "point_rating_method": "sequential_elo",
          "public_id": "E-d5866895bf388f66",
          "rated_matches": 96,
          "raw_elo_rating": 1646.602219075191,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 62.30025511722427,
          "uncertainty": 7.017308256680951,
          "unilateral_faults": 0,
          "wins": 64
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 122,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 60,
          "draws": 1,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 73,
          "model": "gpt-5.5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-1ea2c2c23d752166",
          "rated_matches": 122,
          "raw_elo_rating": 1468.311575824817,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 47.27455398323267,
          "uncertainty": 1.3334817333716131,
          "unilateral_faults": 0,
          "wins": 48
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 84,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 41,
          "draws": 5,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "xhigh",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 16,
          "model": "gpt-5.5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-4175a77ccf4c269b",
          "rated_matches": 84,
          "raw_elo_rating": 1909.8196476234893,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "xhigh",
          "repair_status": "first_pass",
          "score": 84.82408848503748,
          "uncertainty": 10.482614454664043,
          "unilateral_faults": 0,
          "wins": 63
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 92,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 43,
          "draws": 3,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.6-luna",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 32,
          "model": "gpt-5.6-luna",
          "point_rating_method": "sequential_elo",
          "public_id": "E-6e5d5789ae1ea092",
          "rated_matches": 91,
          "raw_elo_rating": 1617.2068115368675,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 59.663897931635695,
          "uncertainty": 8.378603514268699,
          "unilateral_faults": 1,
          "wins": 56
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 86,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 38,
          "draws": 10,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "xhigh",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.6-luna",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-10T05:30:29Z",
          "losses": 22,
          "model": "gpt-5.6-luna",
          "point_rating_method": "sequential_elo",
          "public_id": "E-9eafeacabdedfdba",
          "rated_matches": 86,
          "raw_elo_rating": 1790.7895280558996,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "xhigh",
          "repair_status": "first_pass",
          "score": 74.57349828912908,
          "uncertainty": 9.855626741889738,
          "unilateral_faults": 0,
          "wins": 54
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 90,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 44,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.6-luna",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-10T05:30:29Z",
          "losses": 81,
          "model": "gpt-5.6-luna",
          "point_rating_method": "sequential_elo",
          "public_id": "E-ae522f9c5c491f57",
          "rated_matches": 90,
          "raw_elo_rating": 978.4527453835951,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 4.4033748279235585,
          "uncertainty": 8.664241836095918,
          "unilateral_faults": 0,
          "wins": 9
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 92,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 44,
          "draws": 3,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.6-luna",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 74,
          "model": "gpt-5.6-luna",
          "point_rating_method": "sequential_elo",
          "public_id": "E-d7a21b3fb5bd3acb",
          "rated_matches": 92,
          "raw_elo_rating": 1192.954172313164,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 22.993102472928516,
          "uncertainty": 8.09758473652126,
          "unilateral_faults": 0,
          "wins": 15
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 90,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 42,
          "draws": 8,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "xhigh",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.6-luna",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 9,
          "model": "gpt-5.6-luna",
          "point_rating_method": "sequential_elo",
          "public_id": "E-d8cf92ac05965d5e",
          "rated_matches": 89,
          "raw_elo_rating": 1876.2466265033572,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "xhigh",
          "repair_status": "first_pass",
          "score": 82.02633954021168,
          "uncertainty": 8.954627669472988,
          "unilateral_faults": 0,
          "wins": 72
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 108,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 52,
          "draws": 8,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.6-luna",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-10T10:07:13Z",
          "losses": 34,
          "model": "gpt-5.6-luna",
          "point_rating_method": "sequential_elo",
          "public_id": "E-f4c50b1a9cf2c2e6",
          "rated_matches": 108,
          "raw_elo_rating": 1693.5219286366255,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 66.55694526663,
          "uncertainty": 4.1413142610575715,
          "unilateral_faults": 0,
          "wins": 66
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 93,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 43,
          "draws": 3,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.6-sol",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 28,
          "model": "gpt-5.6-sol",
          "point_rating_method": "sequential_elo",
          "public_id": "E-69b849005fbfc624",
          "rated_matches": 93,
          "raw_elo_rating": 1656.6269296223352,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 63.111604396432526,
          "uncertainty": 7.821062312939668,
          "unilateral_faults": 0,
          "wins": 62
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 100,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 49,
          "draws": 3,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.6-sol",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-10T05:30:29Z",
          "losses": 58,
          "model": "gpt-5.6-sol",
          "point_rating_method": "sequential_elo",
          "public_id": "E-992b9a5ebbb74c80",
          "rated_matches": 100,
          "raw_elo_rating": 1364.2292853844367,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 37.95031944195105,
          "uncertainty": 6.001859510499461,
          "unilateral_faults": 0,
          "wins": 39
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 92,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 43,
          "draws": 1,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.6-sol",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 53,
          "model": "gpt-5.6-sol",
          "point_rating_method": "sequential_elo",
          "public_id": "E-a106eb47f4726fc8",
          "rated_matches": 92,
          "raw_elo_rating": 1325.565033749482,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 34.46156161117417,
          "uncertainty": 8.09758473652126,
          "unilateral_faults": 0,
          "wins": 38
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 92,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 45,
          "draws": 12,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.6-sol",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-10T10:07:13Z",
          "losses": 16,
          "model": "gpt-5.6-sol",
          "point_rating_method": "sequential_elo",
          "public_id": "E-acdece52463a2698",
          "rated_matches": 92,
          "raw_elo_rating": 1817.2618046108626,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 76.98450629273803,
          "uncertainty": 8.09758473652126,
          "unilateral_faults": 0,
          "wins": 64
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 86,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 40,
          "draws": 3,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "xhigh",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.6-sol",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-10T05:30:29Z",
          "losses": 23,
          "model": "gpt-5.6-sol",
          "point_rating_method": "sequential_elo",
          "public_id": "E-eb315c759774ef38",
          "rated_matches": 86,
          "raw_elo_rating": 1810.9235349193502,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "xhigh",
          "repair_status": "first_pass",
          "score": 76.31472847571924,
          "uncertainty": 9.855626741889738,
          "unilateral_faults": 0,
          "wins": 60
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 90,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 43,
          "draws": 6,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "xhigh",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.6-sol",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 1,
          "model": "gpt-5.6-sol",
          "point_rating_method": "sequential_elo",
          "public_id": "E-edb238a0d9a72c9f",
          "rated_matches": 90,
          "raw_elo_rating": 1996.2299624147333,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "xhigh",
          "repair_status": "first_pass",
          "score": 92.42283491539342,
          "uncertainty": 8.664241836095918,
          "unilateral_faults": 0,
          "wins": 83
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 102,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 50,
          "draws": 2,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.6-terra",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-10T05:30:29Z",
          "losses": 53,
          "model": "gpt-5.6-terra",
          "point_rating_method": "sequential_elo",
          "public_id": "E-22ffdca36d9bac9c",
          "rated_matches": 102,
          "raw_elo_rating": 1373.9806181391325,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 38.82721709336295,
          "uncertainty": 5.516463908214657,
          "unilateral_faults": 0,
          "wins": 47
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 102,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 51,
          "draws": 12,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.6-terra",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-10T05:30:29Z",
          "losses": 42,
          "model": "gpt-5.6-terra",
          "point_rating_method": "sequential_elo",
          "public_id": "E-a3722334e358f0fe",
          "rated_matches": 102,
          "raw_elo_rating": 1502.2749957494511,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 49.922377861903456,
          "uncertainty": 5.516463908214657,
          "unilateral_faults": 0,
          "wins": 48
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 92,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 44,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "xhigh",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.6-terra",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-10T05:30:29Z",
          "losses": 34,
          "model": "gpt-5.6-terra",
          "point_rating_method": "sequential_elo",
          "public_id": "E-e6571a10c1120fab",
          "rated_matches": 92,
          "raw_elo_rating": 1762.4255362201798,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "xhigh",
          "repair_status": "first_pass",
          "score": 72.24215339252389,
          "uncertainty": 8.09758473652126,
          "unilateral_faults": 0,
          "wins": 58
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 130,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 51,
          "draws": 4,
          "evaluated_setting_identity": {
            "canonical_provider_route": "unknown_legacy",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "inclusionai/ling-3.0-flash:free",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 70,
          "model": "inclusionai/ling-3.0-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-6807fffacebac165",
          "rated_matches": 130,
          "raw_elo_rating": 1285.4838250666692,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 31.559976136514084,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 56
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 52,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 26,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "unknown_legacy",
            "effective_request_value": "enabled",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "inclusionai/ling-3.0-flash:free",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 37,
          "model": "inclusionai/ling-3.0-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-6c37c8c2b8e19c4c",
          "rated_matches": 52,
          "raw_elo_rating": 1302.5238444195195,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "enabled",
          "repair_status": "repaired",
          "score": 31.30433139519322,
          "uncertainty": 24.930281974344517,
          "unilateral_faults": 0,
          "wins": 15
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 128,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 49,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "unknown_legacy",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "inclusionai/ling-3.0-flash:free",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 122,
          "model": "inclusionai/ling-3.0-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-9bde0475193e2c4a",
          "rated_matches": 128,
          "raw_elo_rating": 920.8227548067191,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "none",
          "repair_status": "repaired",
          "score": 0.0,
          "uncertainty": 0.27254531628119416,
          "unilateral_faults": 0,
          "wins": 6
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 164,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 61,
          "draws": 11,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "enabled",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "meituan/longcat-2.0",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 115,
          "model": "meituan/longcat-2.0",
          "point_rating_method": "sequential_elo",
          "public_id": "E-0e252768ba2388c4",
          "rated_matches": 164,
          "raw_elo_rating": 1192.2405949843633,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "enabled",
          "repair_status": "first_pass",
          "score": 23.825451789793053,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 38
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 118,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 57,
          "draws": 6,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "meituan/longcat-2.0",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 65,
          "model": "meituan/longcat-2.0",
          "point_rating_method": "sequential_elo",
          "public_id": "E-3e8b2d11481a50d7",
          "rated_matches": 118,
          "raw_elo_rating": 1375.1951763308493,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "none",
          "repair_status": "repaired",
          "score": 39.16966780112746,
          "uncertainty": 2.084924851410568,
          "unilateral_faults": 0,
          "wins": 47
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 182,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 70,
          "draws": 12,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "enabled",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "meituan/longcat-2.0",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 112,
          "model": "meituan/longcat-2.0",
          "point_rating_method": "sequential_elo",
          "public_id": "E-a9bdeb6a9326ac2d",
          "rated_matches": 182,
          "raw_elo_rating": 1341.1810383570273,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "enabled",
          "repair_status": "repaired",
          "score": 36.841999195974246,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 58
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 98,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 49,
          "draws": 14,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "meituan/longcat-2.0",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 43,
          "model": "meituan/longcat-2.0",
          "point_rating_method": "sequential_elo",
          "public_id": "E-e3023ff7ecf82fc4",
          "rated_matches": 98,
          "raw_elo_rating": 1541.6697695437547,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "none",
          "repair_status": "repaired",
          "score": 53.26114126809031,
          "uncertainty": 6.501890762960602,
          "unilateral_faults": 0,
          "wins": 41
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 94,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 43,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "minimal",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "meta/muse-spark-1.2",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-08-13T16:58:34Z",
          "losses": 69,
          "model": "meta/muse-spark-1.2",
          "point_rating_method": "sequential_elo",
          "public_id": "E-f5d3d04141e68bd0",
          "rated_matches": 94,
          "raw_elo_rating": 1250.7317045501534,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "minimal",
          "repair_status": "repaired",
          "score": 28.027781786573513,
          "uncertainty": 7.54891760425771,
          "unilateral_faults": 0,
          "wins": 25
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 120,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 59,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "enabled",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "minimax/minimax-m3",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 79,
          "model": "minimax/minimax-m3",
          "point_rating_method": "sequential_elo",
          "public_id": "E-ef8c1a9fa3580f83",
          "rated_matches": 120,
          "raw_elo_rating": 1342.8613766220567,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "enabled",
          "repair_status": "repaired",
          "score": 36.399691312701414,
          "uncertainty": 1.7045454545454586,
          "unilateral_faults": 0,
          "wins": 41
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 90,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 44,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "mistralai/mistral-medium-3-5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 62,
          "model": "mistralai/mistral-medium-3-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-6c35f5ff426e7ada",
          "rated_matches": 90,
          "raw_elo_rating": 1253.7221512485582,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "repaired",
          "score": 28.20923732650551,
          "uncertainty": 8.664241836095918,
          "unilateral_faults": 0,
          "wins": 28
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 90,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 44,
          "draws": 8,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "mistralai/mistral-medium-3-5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 47,
          "model": "mistralai/mistral-medium-3-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-cf0bc4a1e7a8d72a",
          "rated_matches": 90,
          "raw_elo_rating": 1323.4952044044514,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "repaired",
          "score": 34.24335399238109,
          "uncertainty": 8.664241836095918,
          "unilateral_faults": 0,
          "wins": 35
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 190,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 73,
          "draws": 16,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "moonshotai/kimi-k3",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T14:00:00Z",
          "losses": 74,
          "model": "moonshotai/kimi-k3",
          "point_rating_method": "sequential_elo",
          "public_id": "E-1640f1438f9390d7",
          "rated_matches": 190,
          "raw_elo_rating": 1661.6059928496998,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "repaired",
          "score": 64.6071323338313,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 100
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 184,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 68,
          "draws": 20,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "low",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "moonshotai/kimi-k3",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T14:00:00Z",
          "losses": 70,
          "model": "moonshotai/kimi-k3",
          "point_rating_method": "sequential_elo",
          "public_id": "E-95a5c0e17cd4b70a",
          "rated_matches": 184,
          "raw_elo_rating": 1623.3658987890403,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "low",
          "repair_status": "first_pass",
          "score": 61.25978450989219,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 94
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 106,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 52,
          "draws": 10,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "enabled",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "nex-agi/nex-n2-pro",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 76,
          "model": "nex-agi/nex-n2-pro",
          "point_rating_method": "sequential_elo",
          "public_id": "E-209380b737b62580",
          "rated_matches": 106,
          "raw_elo_rating": 1195.0146527344775,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "enabled",
          "repair_status": "repaired",
          "score": 23.41419124049507,
          "uncertainty": 4.586824452283178,
          "unilateral_faults": 0,
          "wins": 20
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 92,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 45,
          "draws": 2,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "nex-agi/nex-n2-pro",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-11T17:22:09Z",
          "losses": 67,
          "model": "nex-agi/nex-n2-pro",
          "point_rating_method": "sequential_elo",
          "public_id": "E-973417dedd770061",
          "rated_matches": 92,
          "raw_elo_rating": 1204.3990254582595,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "none",
          "repair_status": "repaired",
          "score": 23.982876833913124,
          "uncertainty": 8.09758473652126,
          "unilateral_faults": 0,
          "wins": 23
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 98,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 47,
          "draws": 8,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "nvidia/nemotron-3-ultra-550b-a55b",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 37,
          "model": "nvidia/nemotron-3-ultra-550b-a55b",
          "point_rating_method": "sequential_elo",
          "public_id": "E-1ea0c8193f35ca72",
          "rated_matches": 98,
          "raw_elo_rating": 1625.0173972189637,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "repaired",
          "score": 60.46921496514469,
          "uncertainty": 6.501890762960602,
          "unilateral_faults": 0,
          "wins": 53
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 80,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 40,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "nvidia/nemotron-3-ultra-550b-a55b",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 49,
          "model": "nvidia/nemotron-3-ultra-550b-a55b",
          "point_rating_method": "sequential_elo",
          "public_id": "E-6e76a1c11ba24bc6",
          "rated_matches": 80,
          "raw_elo_rating": 1244.3425660567527,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "repaired",
          "score": 27.180737771836384,
          "uncertainty": 11.805555555555554,
          "unilateral_faults": 0,
          "wins": 31
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 91,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 46,
          "draws": 7,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "nvidia/nemotron-3-ultra-550b-a55b",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-11T17:22:09Z",
          "losses": 59,
          "model": "nvidia/nemotron-3-ultra-550b-a55b",
          "point_rating_method": "sequential_elo",
          "public_id": "E-ba2fb1c121873708",
          "rated_matches": 91,
          "raw_elo_rating": 1392.9558533954528,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "repaired",
          "score": 40.27021537575938,
          "uncertainty": 8.378603514268699,
          "unilateral_faults": 0,
          "wins": 25
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 150,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 51,
          "draws": 4,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "o3",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-03T16:00:00Z",
          "losses": 64,
          "model": "o3",
          "point_rating_method": "sequential_elo",
          "public_id": "E-2c94ff7a30958259",
          "rated_matches": 150,
          "raw_elo_rating": 1560.59701847636,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "first_pass",
          "score": 55.55959401084185,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 82
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 151,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 52,
          "draws": 3,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "o3",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-03T15:50:00Z",
          "losses": 65,
          "model": "o3",
          "point_rating_method": "sequential_elo",
          "public_id": "E-35751e26cd4e995d",
          "rated_matches": 151,
          "raw_elo_rating": 1506.9742217936025,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "first_pass",
          "score": 50.93146018801068,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 83
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 146,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 52,
          "draws": 6,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "o3",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 105,
          "model": "o3",
          "point_rating_method": "sequential_elo",
          "public_id": "E-432424671c9fea1c",
          "rated_matches": 146,
          "raw_elo_rating": 1217.3723017703346,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "first_pass",
          "score": 25.83877298968737,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 35
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 106,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 52,
          "draws": 11,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "o3",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 43,
          "model": "o3",
          "point_rating_method": "sequential_elo",
          "public_id": "E-69e964db7b91b1bb",
          "rated_matches": 106,
          "raw_elo_rating": 1597.6476744413671,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 58.234720321902785,
          "uncertainty": 4.586824452283178,
          "unilateral_faults": 0,
          "wins": 52
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 168,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 62,
          "draws": 26,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "low",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "o3",
            "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-21T14:20:15Z",
          "losses": 115,
          "model": "o3",
          "point_rating_method": "sequential_elo",
          "public_id": "E-9f2773793ec1d7e3",
          "rated_matches": 168,
          "raw_elo_rating": 1154.7845709020912,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "low",
          "repair_status": "first_pass",
          "score": 20.618239276105058,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 27
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 144,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 50,
          "draws": 4,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "o3",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-03T15:45:00Z",
          "losses": 52,
          "model": "o3",
          "point_rating_method": "sequential_elo",
          "public_id": "E-ead4229a85e5d554",
          "rated_matches": 144,
          "raw_elo_rating": 1661.179264242441,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "first_pass",
          "score": 64.20049924082426,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 88
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 88,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 42,
          "draws": 6,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "openai/gpt-oss-120b",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 32,
          "model": "openai/gpt-oss-120b",
          "point_rating_method": "sequential_elo",
          "public_id": "E-a97b527d9b41a80c",
          "rated_matches": 88,
          "raw_elo_rating": 1712.237284828002,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "repaired",
          "score": 67.82204727657161,
          "uncertainty": 9.249894000318006,
          "unilateral_faults": 0,
          "wins": 50
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 171,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 67,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "low",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "openai/gpt-oss-120b",
            "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-21T14:20:15Z",
          "losses": 121,
          "model": "openai/gpt-oss-120b",
          "point_rating_method": "sequential_elo",
          "public_id": "E-b75de88bfc62ab22",
          "rated_matches": 171,
          "raw_elo_rating": 1181.1910568908093,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "low",
          "repair_status": "first_pass",
          "score": 22.92523467244584,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 50
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 121,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 59,
          "draws": 1,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "openai/gpt-oss-120b",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 78,
          "model": "openai/gpt-oss-120b",
          "point_rating_method": "sequential_elo",
          "public_id": "E-f225b6990e542d31",
          "rated_matches": 121,
          "raw_elo_rating": 1340.0030877685297,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "repaired",
          "score": 36.16541568514887,
          "uncertainty": 1.5178730212592662,
          "unilateral_faults": 0,
          "wins": 42
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 108,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 52,
          "draws": 4,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "poolside/laguna-s-2.1",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 58,
          "model": "poolside/laguna-s-2.1",
          "point_rating_method": "sequential_elo",
          "public_id": "E-a29031412bc33c39",
          "rated_matches": 108,
          "raw_elo_rating": 1210.0954507274137,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 24.749232472982165,
          "uncertainty": 4.1413142610575715,
          "unilateral_faults": 0,
          "wins": 46
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 176,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 66,
          "draws": 7,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "enabled",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "poolside/laguna-s-2.1",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 125,
          "model": "poolside/laguna-s-2.1",
          "point_rating_method": "sequential_elo",
          "public_id": "E-b582570ce841ee30",
          "rated_matches": 176,
          "raw_elo_rating": 1156.182973847154,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "enabled",
          "repair_status": "first_pass",
          "score": 20.800006608149722,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 44
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 98,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 47,
          "draws": 2,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "qwen/qwen3.7-max",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 63,
          "model": "qwen/qwen3.7-max",
          "point_rating_method": "sequential_elo",
          "public_id": "E-0c7e9f6c7d4cb892",
          "rated_matches": 98,
          "raw_elo_rating": 1225.4277449994963,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 25.9118827156635,
          "uncertainty": 6.501890762960602,
          "unilateral_faults": 0,
          "wins": 33
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 110,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 52,
          "draws": 12,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "enabled",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "qwen/qwen3.7-max",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 42,
          "model": "qwen/qwen3.7-max",
          "point_rating_method": "sequential_elo",
          "public_id": "E-8283efe6f68a787e",
          "rated_matches": 110,
          "raw_elo_rating": 1579.5531911998273,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "enabled",
          "repair_status": "repaired",
          "score": 56.73068128436687,
          "uncertainty": 3.707899787624953,
          "unilateral_faults": 0,
          "wins": 56
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 99,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 48,
          "draws": 2,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "qwen/qwen3.7-plus",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 71,
          "model": "qwen/qwen3.7-plus",
          "point_rating_method": "sequential_elo",
          "public_id": "E-2fb82a23fdec2792",
          "rated_matches": 99,
          "raw_elo_rating": 1234.4468531079099,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 26.709300896929104,
          "uncertainty": 6.25,
          "unilateral_faults": 0,
          "wins": 26
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 100,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 47,
          "draws": 5,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "enabled",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "qwen/qwen3.7-plus",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 31,
          "model": "qwen/qwen3.7-plus",
          "point_rating_method": "sequential_elo",
          "public_id": "E-b6dd11ebe2b80c7b",
          "rated_matches": 100,
          "raw_elo_rating": 1740.616275075024,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "enabled",
          "repair_status": "repaired",
          "score": 70.50103787240695,
          "uncertainty": 6.001859510499461,
          "unilateral_faults": 0,
          "wins": 64
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 20,
          "capped_draws": 0,
          "coverage_status": "under_covered",
          "distinct_rated_opponents": 10,
          "draws": 1,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "qwen/qwen3.8-max",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 6,
          "model": "qwen/qwen3.8-max",
          "point_rating_method": "sequential_elo",
          "public_id": "E-3f0cae67eaa3db85",
          "rated_matches": 20,
          "raw_elo_rating": 1596.932346317202,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 53.968299220992186,
          "uncertainty": 65.3589451179962,
          "unilateral_faults": 0,
          "wins": 13
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 16,
          "capped_draws": 0,
          "coverage_status": "under_covered",
          "distinct_rated_opponents": 10,
          "draws": 2,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "minimal",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "qwen/qwen3.8-max",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 11,
          "model": "qwen/qwen3.8-max",
          "point_rating_method": "sequential_elo",
          "public_id": "E-5142494e6069cc88",
          "rated_matches": 16,
          "raw_elo_rating": 1320.8161587044958,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "minimal",
          "repair_status": "first_pass",
          "score": 29.24798627908666,
          "uncertainty": 77.5178125181665,
          "unilateral_faults": 0,
          "wins": 3
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 15,
          "capped_draws": 0,
          "coverage_status": "under_covered",
          "distinct_rated_opponents": 9,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "xhigh",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "qwen/qwen3.8-max",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-08-18T17:01:47Z",
          "losses": 7,
          "model": "qwen/qwen3.8-max",
          "point_rating_method": "sequential_elo",
          "public_id": "E-7a5171930c689e38",
          "rated_matches": 15,
          "raw_elo_rating": 1522.7378338885317,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "xhigh",
          "repair_status": "first_pass",
          "score": 46.45237289235433,
          "uncertainty": 81.25,
          "unilateral_faults": 0,
          "wins": 8
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 14,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 7,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "low",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "stealth/ox-alpha",
            "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-08-22T00:27:26Z",
          "losses": 5,
          "model": "stealth/ox-alpha",
          "point_rating_method": "sequential_elo",
          "public_id": "E-026a6a472034feda",
          "rated_matches": 14,
          "raw_elo_rating": 1543.1180286222932,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "low",
          "repair_status": "first_pass",
          "score": 47.9312711936831,
          "uncertainty": 85.34944487358055,
          "unilateral_faults": 0,
          "wins": 9
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 14,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 7,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "stealth/ox-alpha",
            "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-08-22T00:27:26Z",
          "losses": 14,
          "model": "stealth/ox-alpha",
          "point_rating_method": "sequential_elo",
          "public_id": "E-02a3b80bf1513f09",
          "rated_matches": 14,
          "raw_elo_rating": 1327.2247635397769,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "first_pass",
          "score": 29.260379066115735,
          "uncertainty": 85.34944487358055,
          "unilateral_faults": 0,
          "wins": 0
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 14,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 7,
          "draws": 1,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "max",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "stealth/ox-alpha",
            "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-08-22T00:27:26Z",
          "losses": 1,
          "model": "stealth/ox-alpha",
          "point_rating_method": "sequential_elo",
          "public_id": "E-2f1a60fc993600a0",
          "rated_matches": 14,
          "raw_elo_rating": 1635.0373727459369,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "max",
          "repair_status": "repaired",
          "score": 55.88064450050368,
          "uncertainty": 85.34944487358055,
          "unilateral_faults": 0,
          "wins": 12
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 14,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 7,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "low",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "stealth/ox-alpha",
            "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-08-22T00:27:26Z",
          "losses": 6,
          "model": "stealth/ox-alpha",
          "point_rating_method": "sequential_elo",
          "public_id": "E-30880d6c82cf51b1",
          "rated_matches": 14,
          "raw_elo_rating": 1525.0947706738589,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "low",
          "repair_status": "first_pass",
          "score": 46.37258290012322,
          "uncertainty": 85.34944487358055,
          "unilateral_faults": 0,
          "wins": 8
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 14,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 7,
          "draws": 1,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "stealth/ox-alpha",
            "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-08-22T00:27:26Z",
          "losses": 8,
          "model": "stealth/ox-alpha",
          "point_rating_method": "sequential_elo",
          "public_id": "E-3b621d9cad889cf5",
          "rated_matches": 14,
          "raw_elo_rating": 1478.2456762892064,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "repaired",
          "score": 42.32097718099277,
          "uncertainty": 85.34944487358055,
          "unilateral_faults": 0,
          "wins": 5
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 14,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 7,
          "draws": 2,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "max",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "stealth/ox-alpha",
            "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-08-22T00:27:26Z",
          "losses": 0,
          "model": "stealth/ox-alpha",
          "point_rating_method": "sequential_elo",
          "public_id": "E-4d01a918377d78de",
          "rated_matches": 14,
          "raw_elo_rating": 1640.0055339758726,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "max",
          "repair_status": "first_pass",
          "score": 56.31030126798569,
          "uncertainty": 85.34944487358055,
          "unilateral_faults": 0,
          "wins": 12
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 14,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 7,
          "draws": 3,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "max",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "stealth/ox-alpha",
            "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-08-22T00:27:26Z",
          "losses": 7,
          "model": "stealth/ox-alpha",
          "point_rating_method": "sequential_elo",
          "public_id": "E-7c6550006514213b",
          "rated_matches": 14,
          "raw_elo_rating": 1455.9913598877981,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "max",
          "repair_status": "first_pass",
          "score": 40.396378279101896,
          "uncertainty": 85.34944487358055,
          "unilateral_faults": 0,
          "wins": 4
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 14,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 7,
          "draws": 1,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "low",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "stealth/ox-alpha",
            "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-08-22T00:27:26Z",
          "losses": 11,
          "model": "stealth/ox-alpha",
          "point_rating_method": "sequential_elo",
          "public_id": "E-8f80a28afb47af72",
          "rated_matches": 14,
          "raw_elo_rating": 1395.2824942652571,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "low",
          "repair_status": "repaired",
          "score": 35.14615113194093,
          "uncertainty": 85.34944487358055,
          "unilateral_faults": 0,
          "wins": 2
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 106,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 52,
          "draws": 2,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "stepfun/step-3.7-flash",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 64,
          "model": "stepfun/step-3.7-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-2d684425ca56be18",
          "rated_matches": 106,
          "raw_elo_rating": 1412.0094597124114,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "repaired",
          "score": 42.18034696924738,
          "uncertainty": 4.586824452283178,
          "unilateral_faults": 0,
          "wins": 40
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 112,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 56,
          "draws": 1,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "stepfun/step-3.7-flash",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 78,
          "model": "stepfun/step-3.7-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-6526762dce98da7c",
          "rated_matches": 112,
          "raw_elo_rating": 1267.48183370103,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "repaired",
          "score": 29.77129697036285,
          "uncertainty": 3.286043419179858,
          "unilateral_faults": 0,
          "wins": 33
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 164,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 60,
          "draws": 11,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "low",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "stepfun/step-3.7-flash",
            "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-21T14:20:15Z",
          "losses": 68,
          "model": "stepfun/step-3.7-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-ab4ccc8ca01bc627",
          "rated_matches": 164,
          "raw_elo_rating": 1505.431236228724,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "low",
          "repair_status": "first_pass",
          "score": 50.91082045936282,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 85
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 90,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 43,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "tencent/hy3-preview",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 65,
          "model": "tencent/hy3-preview",
          "point_rating_method": "sequential_elo",
          "public_id": "E-3627e3dbf7a48738",
          "rated_matches": 90,
          "raw_elo_rating": 1236.8815002319625,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "first_pass",
          "score": 26.752823304656847,
          "uncertainty": 8.664241836095918,
          "unilateral_faults": 0,
          "wins": 25
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 112,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 54,
          "draws": 1,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "thinkingmachines/inkling",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 58,
          "model": "thinkingmachines/inkling",
          "point_rating_method": "sequential_elo",
          "public_id": "E-02be9616e86c7055",
          "rated_matches": 112,
          "raw_elo_rating": 1315.7125886364151,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "repaired",
          "score": 33.94239152620984,
          "uncertainty": 3.286043419179858,
          "unilateral_faults": 0,
          "wins": 53
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 156,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 54,
          "draws": 8,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "max",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "thinkingmachines/inkling",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 69,
          "model": "thinkingmachines/inkling",
          "point_rating_method": "sequential_elo",
          "public_id": "E-56e54327930d2f64",
          "rated_matches": 156,
          "raw_elo_rating": 1594.5323147640372,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "max",
          "repair_status": "repaired",
          "score": 58.54870417164183,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 79
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 21,
          "capped_draws": 0,
          "coverage_status": "under_covered",
          "distinct_rated_opponents": 10,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "thinkingmachines/inkling-small",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-08-18T19:25:55Z",
          "losses": 15,
          "model": "thinkingmachines/inkling-small",
          "point_rating_method": "sequential_elo",
          "public_id": "E-4166320c34322333",
          "rated_matches": 21,
          "raw_elo_rating": 1368.9037533119765,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "repaired",
          "score": 34.421477251042134,
          "uncertainty": 62.850358177805205,
          "unilateral_faults": 0,
          "wins": 6
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 16,
          "capped_draws": 0,
          "coverage_status": "under_covered",
          "distinct_rated_opponents": 9,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "max",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "thinkingmachines/inkling-small",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-08-18T19:25:55Z",
          "losses": 2,
          "model": "thinkingmachines/inkling-small",
          "point_rating_method": "sequential_elo",
          "public_id": "E-686068814c2242e8",
          "rated_matches": 16,
          "raw_elo_rating": 1608.3676756467582,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "max",
          "repair_status": "first_pass",
          "score": 54.116030920939295,
          "uncertainty": 77.5178125181665,
          "unilateral_faults": 0,
          "wins": 14
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 19,
          "capped_draws": 0,
          "coverage_status": "under_covered",
          "distinct_rated_opponents": 9,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "thinkingmachines/inkling-small",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-08-18T19:25:55Z",
          "losses": 14,
          "model": "thinkingmachines/inkling-small",
          "point_rating_method": "sequential_elo",
          "public_id": "E-76b6aea02c1d6b3d",
          "rated_matches": 19,
          "raw_elo_rating": 1377.382181449011,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "repaired",
          "score": 34.79473339617072,
          "uncertainty": 68.05339887498948,
          "unilateral_faults": 0,
          "wins": 5
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 122,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 59,
          "draws": 8,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "x-ai/grok-4.5",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T14:00:00Z",
          "losses": 62,
          "model": "x-ai/grok-4.5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-3baaff3521870bef",
          "rated_matches": 122,
          "raw_elo_rating": 1443.9671489840152,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 45.169198045990534,
          "uncertainty": 1.3334817333716131,
          "unilateral_faults": 0,
          "wins": 52
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 182,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 65,
          "draws": 13,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "x-ai/grok-4.5",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T14:00:00Z",
          "losses": 82,
          "model": "x-ai/grok-4.5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-5a1e23bce371a184",
          "rated_matches": 182,
          "raw_elo_rating": 1540.3129835742382,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "first_pass",
          "score": 54.06333802227879,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 87
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 163,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 60,
          "draws": 18,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "low",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "x-ai/grok-4.5",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T14:00:00Z",
          "losses": 68,
          "model": "x-ai/grok-4.5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-8dbfeb56f012d9c6",
          "rated_matches": 163,
          "raw_elo_rating": 1506.1558845685156,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "low",
          "repair_status": "first_pass",
          "score": 50.965291500953946,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 77
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 124,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 57,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "enabled",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "x-ai/grok-build-0.1",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 73,
          "model": "x-ai/grok-build-0.1",
          "point_rating_method": "sequential_elo",
          "public_id": "E-133675db0ee21fd5",
          "rated_matches": 124,
          "raw_elo_rating": 1419.0192370849595,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "enabled",
          "repair_status": "repaired",
          "score": 43.0367051388074,
          "uncertainty": 0.9713595499957961,
          "unilateral_faults": 0,
          "wins": 51
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 72,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 36,
          "draws": 7,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "xiaomi/mimo-v2.5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T06:10:40Z",
          "losses": 30,
          "model": "xiaomi/mimo-v2.5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-51421c7ae2af8f7b",
          "rated_matches": 72,
          "raw_elo_rating": 1577.339884678403,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "repaired",
          "score": 55.77389183234963,
          "uncertainty": 14.770573598065289,
          "unilateral_faults": 0,
          "wins": 35
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 124,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 59,
          "draws": 5,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "enabled",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "xiaomi/mimo-v2.5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 77,
          "model": "xiaomi/mimo-v2.5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-7b4c450b6850f156",
          "rated_matches": 124,
          "raw_elo_rating": 1340.4538958273813,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "enabled",
          "repair_status": "repaired",
          "score": 36.242213374439,
          "uncertainty": 0.9713595499957961,
          "unilateral_faults": 0,
          "wins": 42
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 100,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 48,
          "draws": 3,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "xiaomi/mimo-v2.5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 56,
          "model": "xiaomi/mimo-v2.5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-d572bc902e0e416b",
          "rated_matches": 100,
          "raw_elo_rating": 1318.8645561550443,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 34.02708466427257,
          "uncertainty": 6.001859510499461,
          "unilateral_faults": 0,
          "wins": 41
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 82,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 41,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "xiaomi/mimo-v2.5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T06:10:40Z",
          "losses": 48,
          "model": "xiaomi/mimo-v2.5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-d79ad8bc05d1b933",
          "rated_matches": 82,
          "raw_elo_rating": 1351.9395132779148,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "repaired",
          "score": 36.53253371067762,
          "uncertainty": 11.132129994845172,
          "unilateral_faults": 0,
          "wins": 34
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 86,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 43,
          "draws": 1,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "xiaomi/mimo-v2.5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-01T00:15:48Z",
          "losses": 32,
          "model": "xiaomi/mimo-v2.5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-ff7683792b6b3363",
          "rated_matches": 86,
          "raw_elo_rating": 1650.6471645214087,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 62.45369941048074,
          "uncertainty": 9.855626741889738,
          "unilateral_faults": 0,
          "wins": 53
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 110,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 52,
          "draws": 2,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "enabled",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "xiaomi/mimo-v2.5-pro",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 45,
          "model": "xiaomi/mimo-v2.5-pro",
          "point_rating_method": "sequential_elo",
          "public_id": "E-530f82d65699c577",
          "rated_matches": 110,
          "raw_elo_rating": 1677.2246416402638,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "enabled",
          "repair_status": "repaired",
          "score": 65.17750853680307,
          "uncertainty": 3.707899787624953,
          "unilateral_faults": 0,
          "wins": 63
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 102,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 51,
          "draws": 1,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "xiaomi/mimo-v2.5-pro",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 45,
          "model": "xiaomi/mimo-v2.5-pro",
          "point_rating_method": "sequential_elo",
          "public_id": "E-6b662c734cdcff91",
          "rated_matches": 102,
          "raw_elo_rating": 1421.6211054795062,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "none",
          "repair_status": "repaired",
          "score": 42.94726409759388,
          "uncertainty": 5.516463908214657,
          "unilateral_faults": 0,
          "wins": 56
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 78,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 39,
          "draws": 10,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "z-ai/glm-5.2",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-11T14:00:45Z",
          "losses": 32,
          "model": "z-ai/glm-5.2",
          "point_rating_method": "sequential_elo",
          "public_id": "E-657c61c9039ce566",
          "rated_matches": 78,
          "raw_elo_rating": 1500.231437603409,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 49.26218227671022,
          "uncertainty": 12.5043950463012,
          "unilateral_faults": 0,
          "wins": 36
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 72,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 36,
          "draws": 9,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "z-ai/glm-5.2",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-11T17:22:09Z",
          "losses": 25,
          "model": "z-ai/glm-5.2",
          "point_rating_method": "sequential_elo",
          "public_id": "E-bc40affcf893e495",
          "rated_matches": 72,
          "raw_elo_rating": 1689.1739025328532,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "repaired",
          "score": 65.44552694683463,
          "uncertainty": 14.770573598065289,
          "unilateral_faults": 0,
          "wins": 38
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 72,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 36,
          "draws": 6,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "z-ai/glm-5.2",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 33,
          "model": "z-ai/glm-5.2",
          "point_rating_method": "sequential_elo",
          "public_id": "E-ec1479c855f477b4",
          "rated_matches": 72,
          "raw_elo_rating": 1698.8979955999437,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "repaired",
          "score": 66.28648644885837,
          "uncertainty": 14.770573598065289,
          "unilateral_faults": 0,
          "wins": 33
        }
      ],
      "GB2-07": [
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 94,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 44,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "xhigh",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-fable-5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 35,
          "model": "claude-fable-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-babd82321b910e7b",
          "rated_matches": 94,
          "raw_elo_rating": 1735.946996477361,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "xhigh",
          "repair_status": "first_pass",
          "score": 68.72658602086715,
          "uncertainty": 7.54891760425771,
          "unilateral_faults": 0,
          "wins": 59
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 90,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 45,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-fable-5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 20,
          "model": "claude-fable-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-bc12a8303ec2def7",
          "rated_matches": 90,
          "raw_elo_rating": 1769.0766033480754,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 71.7604520313932,
          "uncertainty": 8.664241836095918,
          "unilateral_faults": 0,
          "wins": 70
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 110,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 55,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-opus-4-5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "omitted",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 53,
          "model": "claude-opus-4-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-ca22621c58b6f244",
          "rated_matches": 110,
          "raw_elo_rating": 1463.297529638152,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "omitted",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 43.356649989805135,
          "uncertainty": 3.707899787624953,
          "unilateral_faults": 0,
          "wins": 57
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 196,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 74,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-opus-4-5",
            "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 102,
          "model": "claude-opus-4-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-e7848fdc8b4ffd95",
          "rated_matches": 196,
          "raw_elo_rating": 1557.3437342280079,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 53.09835437853516,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 94
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 170,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 61,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-opus-4-5",
            "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 77,
          "model": "claude-opus-4-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-e8719bed57f17312",
          "rated_matches": 170,
          "raw_elo_rating": 1502.1314410426282,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "first_pass",
          "score": 47.705624366124106,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 93
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 0,
          "capped_draws": 0,
          "coverage_status": "pending",
          "distinct_rated_opponents": 0,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "legacy_shared_thinking_budget",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-opus-4-5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "budget",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 0,
          "model": "claude-opus-4-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-ed9657bcd9dfeda4",
          "rated_matches": 0,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "budget",
          "reasoning_setting": "legacy_shared_thinking_budget",
          "repair_status": "first_pass",
          "unilateral_faults": 0,
          "wins": 0
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 0,
          "capped_draws": 0,
          "coverage_status": "pending",
          "distinct_rated_opponents": 0,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "legacy_shared_thinking_budget",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-opus-4-5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "budget",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 0,
          "model": "claude-opus-4-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-f2d7a3f3bae22998",
          "rated_matches": 0,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "budget",
          "reasoning_setting": "legacy_shared_thinking_budget",
          "repair_status": "first_pass",
          "unilateral_faults": 0,
          "wins": 0
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 102,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 51,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-opus-4-8",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 34,
          "model": "claude-opus-4-8",
          "point_rating_method": "sequential_elo",
          "public_id": "E-0bf7b9ed307db853",
          "rated_matches": 102,
          "raw_elo_rating": 1681.4932621274972,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 63.75494931550506,
          "uncertainty": 5.516463908214657,
          "unilateral_faults": 0,
          "wins": 68
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 94,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 44,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "xhigh",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-opus-4-8",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-03T17:20:00Z",
          "losses": 21,
          "model": "claude-opus-4-8",
          "point_rating_method": "sequential_elo",
          "public_id": "E-5e09cecd1172d99b",
          "rated_matches": 94,
          "raw_elo_rating": 1824.9248359828734,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "xhigh",
          "repair_status": "first_pass",
          "score": 77.1003159963057,
          "uncertainty": 7.54891760425771,
          "unilateral_faults": 0,
          "wins": 73
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 96,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 48,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-opus-4-8",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "omitted",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 39,
          "model": "claude-opus-4-8",
          "point_rating_method": "sequential_elo",
          "public_id": "E-76804598cce96e62",
          "rated_matches": 96,
          "raw_elo_rating": 1550.4563465439146,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "omitted",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 51.31003172352387,
          "uncertainty": 7.017308256680951,
          "unilateral_faults": 0,
          "wins": 57
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 82,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 37,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "xhigh",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-opus-5",
            "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-25T10:50:00Z",
          "losses": 1,
          "model": "claude-opus-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-1e882072d8d97548",
          "rated_matches": 82,
          "raw_elo_rating": 2071.119577926703,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "xhigh",
          "repair_status": "first_pass",
          "score": 100.0,
          "uncertainty": 11.132129994845172,
          "unilateral_faults": 0,
          "wins": 81
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 88,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 44,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-opus-5",
            "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-25T10:50:00Z",
          "losses": 5,
          "model": "claude-opus-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-54bca3ce32fa85ae",
          "rated_matches": 88,
          "raw_elo_rating": 2001.5151284863136,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 93.5912155307729,
          "uncertainty": 9.249894000318006,
          "unilateral_faults": 0,
          "wins": 83
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 100,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 50,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-opus-5",
            "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-25T10:50:00Z",
          "losses": 22,
          "model": "claude-opus-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-914b104a64ab3110",
          "rated_matches": 100,
          "raw_elo_rating": 1856.1879837603456,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 80.15897505759567,
          "uncertainty": 6.001859510499461,
          "unilateral_faults": 0,
          "wins": 78
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 108,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 54,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-opus-5",
            "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-25T10:50:00Z",
          "losses": 28,
          "model": "claude-opus-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-de5e72176c4f0dc9",
          "rated_matches": 108,
          "raw_elo_rating": 1841.6595764381452,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 78.93177963820368,
          "uncertainty": 4.1413142610575715,
          "unilateral_faults": 0,
          "wins": 80
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 108,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 51,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "xhigh",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-sonnet-5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-03T16:50:00Z",
          "losses": 57,
          "model": "claude-sonnet-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-2146a36b46e938d6",
          "rated_matches": 108,
          "raw_elo_rating": 1474.8322523216139,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "xhigh",
          "repair_status": "first_pass",
          "score": 44.40955503896284,
          "uncertainty": 4.1413142610575715,
          "unilateral_faults": 0,
          "wins": 51
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 88,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 42,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-sonnet-5",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 52,
          "model": "claude-sonnet-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-754e53d1d8048114",
          "rated_matches": 88,
          "raw_elo_rating": 1404.3673294676476,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 37.39346503245966,
          "uncertainty": 9.249894000318006,
          "unilateral_faults": 0,
          "wins": 36
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 124,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 60,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-sonnet-5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 52,
          "model": "claude-sonnet-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-9e40526fba9fa8b9",
          "rated_matches": 124,
          "raw_elo_rating": 1528.418380946387,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 49.69122123778862,
          "uncertainty": 0.9713595499957961,
          "unilateral_faults": 0,
          "wins": 72
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 90,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 42,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-sonnet-5",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 39,
          "model": "claude-sonnet-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-a0f9e38d7d75c542",
          "rated_matches": 90,
          "raw_elo_rating": 1538.9093254268835,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 50.09934354410103,
          "uncertainty": 8.664241836095918,
          "unilateral_faults": 0,
          "wins": 51
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 96,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 48,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-sonnet-5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 44,
          "model": "claude-sonnet-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-cd6f193a087d8c8d",
          "rated_matches": 96,
          "raw_elo_rating": 1604.343784837266,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 56.38139398455826,
          "uncertainty": 7.017308256680951,
          "unilateral_faults": 0,
          "wins": 52
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 92,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 42,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "xhigh",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-sonnet-5",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 22,
          "model": "claude-sonnet-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-d751b3c423ad89f1",
          "rated_matches": 92,
          "raw_elo_rating": 1731.131155491913,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "xhigh",
          "repair_status": "first_pass",
          "score": 68.23205766874142,
          "uncertainty": 8.09758473652126,
          "unilateral_faults": 0,
          "wins": 70
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 76,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 38,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "unknown_legacy",
            "effective_request_value": "enabled",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "cohere/north-mini-code:free",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 47,
          "model": "cohere/north-mini-code",
          "point_rating_method": "sequential_elo",
          "public_id": "E-1c961fde1b53f0eb",
          "rated_matches": 76,
          "raw_elo_rating": 1378.8995385942992,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "enabled",
          "repair_status": "repaired",
          "score": 34.697007101399166,
          "uncertainty": 13.230288229818967,
          "unilateral_faults": 0,
          "wins": 29
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 100,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 46,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "unknown_legacy",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "cohere/north-mini-code:free",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 51,
          "model": "cohere/north-mini-code",
          "point_rating_method": "sequential_elo",
          "public_id": "E-3b908f26a42804a4",
          "rated_matches": 100,
          "raw_elo_rating": 1433.728927617014,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 40.4012322141799,
          "uncertainty": 6.001859510499461,
          "unilateral_faults": 0,
          "wins": 49
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 94,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 43,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "unknown_legacy",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "cohere/north-mini-code:free",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-11T17:22:09Z",
          "losses": 79,
          "model": "cohere/north-mini-code",
          "point_rating_method": "sequential_elo",
          "public_id": "E-c7f5dc6d5d3c2a8d",
          "rated_matches": 90,
          "raw_elo_rating": 1101.4407853335463,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "none",
          "repair_status": "repaired",
          "score": 8.929053864680773,
          "uncertainty": 8.664241836095918,
          "unilateral_faults": 4,
          "wins": 11
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 76,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 38,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "deepseek/deepseek-v4-flash",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-01T00:15:48Z",
          "losses": 49,
          "model": "deepseek/deepseek-v4-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-8f2f6c973751f183",
          "rated_matches": 76,
          "raw_elo_rating": 1320.1500414871316,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 29.168075092011048,
          "uncertainty": 13.230288229818967,
          "unilateral_faults": 0,
          "wins": 27
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 84,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 42,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "deepseek/deepseek-v4-flash",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 48,
          "model": "deepseek/deepseek-v4-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-c394c0713cfcfaa4",
          "rated_matches": 84,
          "raw_elo_rating": 1337.0075281912582,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 30.9614054899469,
          "uncertainty": 10.482614454664043,
          "unilateral_faults": 0,
          "wins": 36
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 96,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 45,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "xhigh",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "deepseek/deepseek-v4-flash",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 31,
          "model": "deepseek/deepseek-v4-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-ecf2a6ea6f9fe06c",
          "rated_matches": 96,
          "raw_elo_rating": 1770.709939839599,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "xhigh",
          "repair_status": "first_pass",
          "score": 72.03816050961174,
          "uncertainty": 7.017308256680951,
          "unilateral_faults": 0,
          "wins": 65
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 76,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 38,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "deepseek/deepseek-v4-flash",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T06:10:40Z",
          "losses": 40,
          "model": "deepseek/deepseek-v4-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-edc2d085c4253ed3",
          "rated_matches": 76,
          "raw_elo_rating": 1490.5838262704146,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 45.20764742146505,
          "uncertainty": 13.230288229818967,
          "unilateral_faults": 0,
          "wins": 36
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 100,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 48,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "xhigh",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "deepseek/deepseek-v4-pro",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 56,
          "model": "deepseek/deepseek-v4-pro",
          "point_rating_method": "sequential_elo",
          "public_id": "E-f398fd6ac8c8bada",
          "rated_matches": 100,
          "raw_elo_rating": 1598.2368673537846,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "xhigh",
          "repair_status": "repaired",
          "score": 55.8831215680576,
          "uncertainty": 6.001859510499461,
          "unilateral_faults": 0,
          "wins": 44
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 100,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 49,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "deepseek/deepseek-v4-pro",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 43,
          "model": "deepseek/deepseek-v4-pro",
          "point_rating_method": "sequential_elo",
          "public_id": "E-f76d96b0f3163d4b",
          "rated_matches": 100,
          "raw_elo_rating": 1445.5598229415996,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "repaired",
          "score": 41.51464116371525,
          "uncertainty": 6.001859510499461,
          "unilateral_faults": 0,
          "wins": 57
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 106,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 51,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "google/gemini-3.1-flash-lite",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 70,
          "model": "google/gemini-3.1-flash-lite",
          "point_rating_method": "sequential_elo",
          "public_id": "E-0d43f308cfa4da52",
          "rated_matches": 106,
          "raw_elo_rating": 1479.7936186306395,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "repaired",
          "score": 44.84292897073299,
          "uncertainty": 4.586824452283178,
          "unilateral_faults": 0,
          "wins": 36
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 94,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 45,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "google/gemini-3.1-flash-lite",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 82,
          "model": "google/gemini-3.1-flash-lite",
          "point_rating_method": "sequential_elo",
          "public_id": "E-1b3c52da51dfbdd4",
          "rated_matches": 94,
          "raw_elo_rating": 1011.5193889215823,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "repaired",
          "score": 0.5504962648416883,
          "uncertainty": 7.54891760425771,
          "unilateral_faults": 0,
          "wins": 12
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 74,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 37,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "google/gemini-3.1-flash-lite",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 70,
          "model": "google/gemini-3.1-flash-lite",
          "point_rating_method": "sequential_elo",
          "public_id": "E-3d6a15fe821fe6ad",
          "rated_matches": 74,
          "raw_elo_rating": 1010.8187961005,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 0.0,
          "uncertainty": 13.985026918962571,
          "unilateral_faults": 0,
          "wins": 4
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 108,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 53,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "google/gemini-3.5-flash",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 53,
          "model": "google/gemini-3.5-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-5447c508e2b0ab6c",
          "rated_matches": 108,
          "raw_elo_rating": 1543.7114866663292,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "repaired",
          "score": 50.89179952279148,
          "uncertainty": 4.1413142610575715,
          "unilateral_faults": 0,
          "wins": 55
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 0,
          "capped_draws": 0,
          "coverage_status": "pending",
          "distinct_rated_opponents": 0,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "low",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "google/gemini-3.5-flash",
            "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-21T14:20:15Z",
          "losses": 0,
          "model": "google/gemini-3.5-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-c9fe3c158f1169e0",
          "rated_matches": 0,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "low",
          "repair_status": "first_pass",
          "unilateral_faults": 0,
          "wins": 0
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 88,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 42,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "google/gemini-3.5-flash",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 42,
          "model": "google/gemini-3.5-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-f7f306cca2bb9532",
          "rated_matches": 88,
          "raw_elo_rating": 1663.7552103873281,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "repaired",
          "score": 61.804532842080334,
          "uncertainty": 9.249894000318006,
          "unilateral_faults": 0,
          "wins": 46
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 146,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 57,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "minimal",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "google/gemini-3.5-flash-lite",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 68,
          "model": "google/gemini-3.5-flash-lite",
          "point_rating_method": "sequential_elo",
          "public_id": "E-455ee67905f5f955",
          "rated_matches": 146,
          "raw_elo_rating": 1628.2860708460423,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "minimal",
          "repair_status": "first_pass",
          "score": 59.351955880308026,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 78
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 158,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 56,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "google/gemini-3.5-flash-lite",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 86,
          "model": "google/gemini-3.5-flash-lite",
          "point_rating_method": "sequential_elo",
          "public_id": "E-c4d27e5c752afb39",
          "rated_matches": 158,
          "raw_elo_rating": 1458.5252459156131,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "first_pass",
          "score": 43.49517776045333,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 72
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 152,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 60,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "minimal",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "google/gemini-3.5-flash-lite",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 29,
          "model": "google/gemini-3.5-flash-lite",
          "point_rating_method": "sequential_elo",
          "public_id": "E-e2e240babaf0b862",
          "rated_matches": 152,
          "raw_elo_rating": 1840.53891009651,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "minimal",
          "repair_status": "first_pass",
          "score": 79.38861936508546,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 123
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 156,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 62,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "google/gemini-3.5-flash-lite",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 117,
          "model": "google/gemini-3.5-flash-lite",
          "point_rating_method": "sequential_elo",
          "public_id": "E-f74134262b66367b",
          "rated_matches": 156,
          "raw_elo_rating": 1158.879352478688,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 15.276461919221447,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 39
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 157,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 60,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "google/gemini-3.5-flash-lite",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 76,
          "model": "google/gemini-3.5-flash-lite",
          "point_rating_method": "sequential_elo",
          "public_id": "E-f746ec3aee7874b2",
          "rated_matches": 157,
          "raw_elo_rating": 1486.0033232989615,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "first_pass",
          "score": 46.071715017764596,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 81
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 156,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 64,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "google/gemini-3.6-flash",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 65,
          "model": "google/gemini-3.6-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-1f7519ff2c4a840c",
          "rated_matches": 156,
          "raw_elo_rating": 1671.4301764240602,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 63.512766849295424,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 91
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 130,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 65,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "google/gemini-3.6-flash",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 55,
          "model": "google/gemini-3.6-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-65c6c8e09fe2c210",
          "rated_matches": 130,
          "raw_elo_rating": 1459.9241308797457,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 43.32321813916118,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 75
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 163,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 56,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "minimal",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "google/gemini-3.6-flash",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 92,
          "model": "google/gemini-3.6-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-8e9b51be911dad38",
          "rated_matches": 159,
          "raw_elo_rating": 1401.9459636158317,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "minimal",
          "repair_status": "first_pass",
          "score": 38.179829200282775,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 67
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 152,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 60,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "minimal",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "google/gemini-3.6-flash",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 55,
          "model": "google/gemini-3.6-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-a2d90fcdc2f4ef9d",
          "rated_matches": 152,
          "raw_elo_rating": 1712.8186002917869,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "minimal",
          "repair_status": "first_pass",
          "score": 67.36882440683803,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 97
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 162,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 59,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "google/gemini-3.6-flash",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 74,
          "model": "google/gemini-3.6-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-f6ecc1626f38fa34",
          "rated_matches": 162,
          "raw_elo_rating": 1503.6788239490022,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "first_pass",
          "score": 47.781451793024814,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 88
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 88,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 43,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "google/gemma-4-31b-it",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 59,
          "model": "google/gemma-4-31b-it",
          "point_rating_method": "sequential_elo",
          "public_id": "E-3f820f7e8ff15839",
          "rated_matches": 86,
          "raw_elo_rating": 1217.1234130773007,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "none",
          "repair_status": "repaired",
          "score": 19.726281854437815,
          "uncertainty": 9.855626741889738,
          "unilateral_faults": 2,
          "wins": 27
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 110,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 52,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "enabled",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "google/gemma-4-31b-it",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 57,
          "model": "google/gemma-4-31b-it",
          "point_rating_method": "sequential_elo",
          "public_id": "E-f417d302c870dfa6",
          "rated_matches": 110,
          "raw_elo_rating": 1408.849027987095,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "enabled",
          "repair_status": "repaired",
          "score": 38.232485895385615,
          "uncertainty": 3.707899787624953,
          "unilateral_faults": 0,
          "wins": 53
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 88,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 44,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-4.1",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "omitted",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 48,
          "model": "gpt-4.1",
          "point_rating_method": "sequential_elo",
          "public_id": "E-fcfa606d3cbb0ba0",
          "rated_matches": 88,
          "raw_elo_rating": 1530.801634444942,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "omitted",
          "reasoning_setting": "none",
          "repair_status": "repaired",
          "score": 49.29223370785008,
          "uncertainty": 9.249894000318006,
          "unilateral_faults": 0,
          "wins": 40
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 96,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 47,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 43,
          "model": "gpt-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-15dad0db253c0497",
          "rated_matches": 96,
          "raw_elo_rating": 1613.540591357989,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "first_pass",
          "score": 57.24690808187588,
          "uncertainty": 7.017308256680951,
          "unilateral_faults": 0,
          "wins": 53
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 100,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 50,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 40,
          "model": "gpt-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-4d8b4cfcff519db6",
          "rated_matches": 100,
          "raw_elo_rating": 1636.8698724185067,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "repaired",
          "score": 59.51888474627783,
          "uncertainty": 6.001859510499461,
          "unilateral_faults": 0,
          "wins": 60
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 0,
          "capped_draws": 0,
          "coverage_status": "pending",
          "distinct_rated_opponents": 0,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "low",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5",
            "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-21T14:20:15Z",
          "losses": 0,
          "model": "gpt-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-a67f59519ca31035",
          "rated_matches": 0,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "low",
          "repair_status": "first_pass",
          "unilateral_faults": 0,
          "wins": 0
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 98,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 43,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.4",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 60,
          "model": "gpt-5.4",
          "point_rating_method": "sequential_elo",
          "public_id": "E-1d11cba509a3ee65",
          "rated_matches": 98,
          "raw_elo_rating": 1388.7768974869502,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 36.13313730855662,
          "uncertainty": 6.501890762960602,
          "unilateral_faults": 0,
          "wins": 38
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 102,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 50,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.4",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 35,
          "model": "gpt-5.4",
          "point_rating_method": "sequential_elo",
          "public_id": "E-22466ae84d7027e5",
          "rated_matches": 102,
          "raw_elo_rating": 1644.7476027576552,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 60.29680478151199,
          "uncertainty": 5.516463908214657,
          "unilateral_faults": 0,
          "wins": 67
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 96,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 42,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.4",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 62,
          "model": "gpt-5.4",
          "point_rating_method": "sequential_elo",
          "public_id": "E-323834608cbfa7f4",
          "rated_matches": 96,
          "raw_elo_rating": 1371.1011530410074,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 34.43086306273809,
          "uncertainty": 7.017308256680951,
          "unilateral_faults": 0,
          "wins": 34
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 98,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 45,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "xhigh",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.4",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 11,
          "model": "gpt-5.4",
          "point_rating_method": "sequential_elo",
          "public_id": "E-80aa3ec3ac4ad97f",
          "rated_matches": 98,
          "raw_elo_rating": 1954.8997479714724,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "xhigh",
          "repair_status": "first_pass",
          "score": 89.41112100908529,
          "uncertainty": 6.501890762960602,
          "unilateral_faults": 0,
          "wins": 87
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 96,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 42,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "xhigh",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.4",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 7,
          "model": "gpt-5.4",
          "point_rating_method": "sequential_elo",
          "public_id": "E-9bc57dfe55b73887",
          "rated_matches": 96,
          "raw_elo_rating": 1906.2070120045769,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "xhigh",
          "repair_status": "first_pass",
          "score": 84.78982880227399,
          "uncertainty": 7.017308256680951,
          "unilateral_faults": 0,
          "wins": 89
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 88,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 44,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.4",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 52,
          "model": "gpt-5.4",
          "point_rating_method": "sequential_elo",
          "public_id": "E-c8176c382cf75e88",
          "rated_matches": 88,
          "raw_elo_rating": 1234.169410217102,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 21.376090075886736,
          "uncertainty": 9.249894000318006,
          "unilateral_faults": 0,
          "wins": 36
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 90,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 44,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.4-mini",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 74,
          "model": "gpt-5.4-mini",
          "point_rating_method": "sequential_elo",
          "public_id": "E-c2ab31787514c10c",
          "rated_matches": 88,
          "raw_elo_rating": 1090.5750082161858,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 7.8623797518037435,
          "uncertainty": 9.249894000318006,
          "unilateral_faults": 2,
          "wins": 14
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 108,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 53,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.4-mini",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 48,
          "model": "gpt-5.4-mini",
          "point_rating_method": "sequential_elo",
          "public_id": "E-f4d7ac8a0f5d2974",
          "rated_matches": 108,
          "raw_elo_rating": 1562.733366371016,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 52.68195407315516,
          "uncertainty": 4.1413142610575715,
          "unilateral_faults": 0,
          "wins": 60
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 100,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 50,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.4-nano",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 62,
          "model": "gpt-5.4-nano",
          "point_rating_method": "sequential_elo",
          "public_id": "E-4e14ae758717169e",
          "rated_matches": 100,
          "raw_elo_rating": 1303.316043587365,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "repaired",
          "score": 28.128038323977535,
          "uncertainty": 6.001859510499461,
          "unilateral_faults": 0,
          "wins": 38
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 94,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 46,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.4-nano",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 78,
          "model": "gpt-5.4-nano",
          "point_rating_method": "sequential_elo",
          "public_id": "E-bea6d7d9558897f9",
          "rated_matches": 94,
          "raw_elo_rating": 1161.1653460942716,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 14.633720180415708,
          "uncertainty": 7.54891760425771,
          "unilateral_faults": 0,
          "wins": 16
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 100,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 50,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.4-nano",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-09T17:30:50Z",
          "losses": 35,
          "model": "gpt-5.4-nano",
          "point_rating_method": "sequential_elo",
          "public_id": "E-ce04fd14b6f43868",
          "rated_matches": 100,
          "raw_elo_rating": 1645.247290829246,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "repaired",
          "score": 60.30728599374183,
          "uncertainty": 6.001859510499461,
          "unilateral_faults": 0,
          "wins": 65
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 112,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 56,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 54,
          "model": "gpt-5.5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-4edfe4117ad3e936",
          "rated_matches": 112,
          "raw_elo_rating": 1464.820592135627,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 43.53174665691214,
          "uncertainty": 3.286043419179858,
          "unilateral_faults": 0,
          "wins": 58
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 98,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 46,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "xhigh",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 6,
          "model": "gpt-5.5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-6201278165db862a",
          "rated_matches": 98,
          "raw_elo_rating": 1985.8838134621776,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "xhigh",
          "repair_status": "first_pass",
          "score": 92.32704029193545,
          "uncertainty": 6.501890762960602,
          "unilateral_faults": 0,
          "wins": 92
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 94,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 46,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 32,
          "model": "gpt-5.5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-640b3078b8bce40e",
          "rated_matches": 94,
          "raw_elo_rating": 1740.3549601868879,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 69.14142074882011,
          "uncertainty": 7.54891760425771,
          "unilateral_faults": 0,
          "wins": 62
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 114,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 54,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.6-luna",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-10T05:30:29Z",
          "losses": 64,
          "model": "gpt-5.6-luna",
          "point_rating_method": "sequential_elo",
          "public_id": "E-45c76cf9faaba10a",
          "rated_matches": 114,
          "raw_elo_rating": 1488.6145781538792,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 45.80193413103889,
          "uncertainty": 2.875240412015687,
          "unilateral_faults": 0,
          "wins": 50
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 96,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 44,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "xhigh",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.6-luna",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-10T05:30:29Z",
          "losses": 29,
          "model": "gpt-5.6-luna",
          "point_rating_method": "sequential_elo",
          "public_id": "E-73a7b73c1df452ad",
          "rated_matches": 96,
          "raw_elo_rating": 1821.0704465715448,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "xhigh",
          "repair_status": "first_pass",
          "score": 76.7776022306421,
          "uncertainty": 7.017308256680951,
          "unilateral_faults": 0,
          "wins": 67
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 92,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 42,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.6-luna",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 79,
          "model": "gpt-5.6-luna",
          "point_rating_method": "sequential_elo",
          "public_id": "E-8fd5624103eac132",
          "rated_matches": 92,
          "raw_elo_rating": 1147.5819193516577,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 13.314071820038254,
          "uncertainty": 8.09758473652126,
          "unilateral_faults": 0,
          "wins": 13
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 90,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 43,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.6-luna",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 61,
          "model": "gpt-5.6-luna",
          "point_rating_method": "sequential_elo",
          "public_id": "E-af6cc32d5ba04b84",
          "rated_matches": 90,
          "raw_elo_rating": 1333.7149739611784,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 30.788444322361737,
          "uncertainty": 8.664241836095918,
          "unilateral_faults": 0,
          "wins": 29
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 90,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 43,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "xhigh",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.6-luna",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 20,
          "model": "gpt-5.6-luna",
          "point_rating_method": "sequential_elo",
          "public_id": "E-d86d2f05318f688d",
          "rated_matches": 90,
          "raw_elo_rating": 1757.382313941039,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "xhigh",
          "repair_status": "first_pass",
          "score": 70.65989910390739,
          "uncertainty": 8.664241836095918,
          "unilateral_faults": 0,
          "wins": 70
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 87,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 43,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.6-luna",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-10T05:30:29Z",
          "losses": 69,
          "model": "gpt-5.6-luna",
          "point_rating_method": "sequential_elo",
          "public_id": "E-ea529147555b5f2e",
          "rated_matches": 86,
          "raw_elo_rating": 1096.9350151518765,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 8.415317281672394,
          "uncertainty": 9.855626741889738,
          "unilateral_faults": 1,
          "wins": 17
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 98,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 45,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "xhigh",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.6-sol",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-10T05:30:29Z",
          "losses": 30,
          "model": "gpt-5.6-sol",
          "point_rating_method": "sequential_elo",
          "public_id": "E-1b522c9c14f3860c",
          "rated_matches": 98,
          "raw_elo_rating": 1649.6684403120166,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "xhigh",
          "repair_status": "first_pass",
          "score": 60.68571517101774,
          "uncertainty": 6.501890762960602,
          "unilateral_faults": 0,
          "wins": 68
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 90,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 42,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "xhigh",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.6-sol",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 1,
          "model": "gpt-5.6-sol",
          "point_rating_method": "sequential_elo",
          "public_id": "E-475950cead6d8909",
          "rated_matches": 90,
          "raw_elo_rating": 1984.8748904849485,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "xhigh",
          "repair_status": "first_pass",
          "score": 92.06929067805841,
          "uncertainty": 8.664241836095918,
          "unilateral_faults": 0,
          "wins": 89
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 92,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 43,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.6-sol",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 11,
          "model": "gpt-5.6-sol",
          "point_rating_method": "sequential_elo",
          "public_id": "E-6e22708296e06d4c",
          "rated_matches": 92,
          "raw_elo_rating": 1850.56158757978,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 79.47168985931388,
          "uncertainty": 8.09758473652126,
          "unilateral_faults": 0,
          "wins": 81
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 92,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 46,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.6-sol",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-10T05:30:29Z",
          "losses": 40,
          "model": "gpt-5.6-sol",
          "point_rating_method": "sequential_elo",
          "public_id": "E-bef852aad169a609",
          "rated_matches": 92,
          "raw_elo_rating": 1643.747048162753,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 60.00831428515665,
          "uncertainty": 8.09758473652126,
          "unilateral_faults": 0,
          "wins": 52
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 98,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 49,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.6-sol",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-10T05:30:29Z",
          "losses": 38,
          "model": "gpt-5.6-sol",
          "point_rating_method": "sequential_elo",
          "public_id": "E-cc78d54d18d4c3f1",
          "rated_matches": 98,
          "raw_elo_rating": 1648.549683693386,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 60.5804286650213,
          "uncertainty": 6.501890762960602,
          "unilateral_faults": 0,
          "wins": 60
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 93,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 43,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.6-sol",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 37,
          "model": "gpt-5.6-sol",
          "point_rating_method": "sequential_elo",
          "public_id": "E-e65ec062f67d1b0b",
          "rated_matches": 93,
          "raw_elo_rating": 1545.286379381379,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 50.76297141256903,
          "uncertainty": 7.821062312939668,
          "unilateral_faults": 0,
          "wins": 56
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 94,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 46,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "xhigh",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.6-terra",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-10T05:30:29Z",
          "losses": 29,
          "model": "gpt-5.6-terra",
          "point_rating_method": "sequential_elo",
          "public_id": "E-65bf9818e3e1b632",
          "rated_matches": 94,
          "raw_elo_rating": 1780.4659593446845,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "xhigh",
          "repair_status": "first_pass",
          "score": 72.91627837470821,
          "uncertainty": 7.54891760425771,
          "unilateral_faults": 0,
          "wins": 65
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 108,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 53,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.6-terra",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-10T05:30:29Z",
          "losses": 60,
          "model": "gpt-5.6-terra",
          "point_rating_method": "sequential_elo",
          "public_id": "E-8ebe8776c7d44d46",
          "rated_matches": 108,
          "raw_elo_rating": 1407.8298422557973,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 38.10393902588812,
          "uncertainty": 4.1413142610575715,
          "unilateral_faults": 0,
          "wins": 48
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 114,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 56,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.6-terra",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-10T05:30:29Z",
          "losses": 59,
          "model": "gpt-5.6-terra",
          "point_rating_method": "sequential_elo",
          "public_id": "E-aca193dd2a8774fb",
          "rated_matches": 114,
          "raw_elo_rating": 1379.3006758761821,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "repaired",
          "score": 35.51437146013137,
          "uncertainty": 2.875240412015687,
          "unilateral_faults": 0,
          "wins": 55
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 52,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 26,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "unknown_legacy",
            "effective_request_value": "enabled",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "inclusionai/ling-3.0-flash:free",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 29,
          "model": "inclusionai/ling-3.0-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-57b2b1d3b488c246",
          "rated_matches": 52,
          "raw_elo_rating": 1479.394616306791,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "enabled",
          "repair_status": "repaired",
          "score": 43.27375585368886,
          "uncertainty": 24.930281974344517,
          "unilateral_faults": 0,
          "wins": 23
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 52,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 26,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "unknown_legacy",
            "effective_request_value": "enabled",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "inclusionai/ling-3.0-flash:free",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 33,
          "model": "inclusionai/ling-3.0-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-5e20a850f6c14680",
          "rated_matches": 52,
          "raw_elo_rating": 1411.6900153869835,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "enabled",
          "repair_status": "repaired",
          "score": 36.90205645810878,
          "uncertainty": 24.930281974344517,
          "unilateral_faults": 0,
          "wins": 19
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 166,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 66,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "enabled",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "meituan/longcat-2.0",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 62,
          "model": "meituan/longcat-2.0",
          "point_rating_method": "sequential_elo",
          "public_id": "E-28ec7bff448d69bb",
          "rated_matches": 166,
          "raw_elo_rating": 1651.2939940426838,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "enabled",
          "repair_status": "first_pass",
          "score": 61.709083324168645,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 104
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 100,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 49,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "meituan/longcat-2.0",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 47,
          "model": "meituan/longcat-2.0",
          "point_rating_method": "sequential_elo",
          "public_id": "E-c1f595f47c71e648",
          "rated_matches": 100,
          "raw_elo_rating": 1378.491617776272,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 35.20283315496975,
          "uncertainty": 6.001859510499461,
          "unilateral_faults": 0,
          "wins": 53
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 108,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 53,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "meituan/longcat-2.0",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 56,
          "model": "meituan/longcat-2.0",
          "point_rating_method": "sequential_elo",
          "public_id": "E-e2db910734ca5315",
          "rated_matches": 108,
          "raw_elo_rating": 1475.8309211848266,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "none",
          "repair_status": "repaired",
          "score": 44.50354005188175,
          "uncertainty": 4.1413142610575715,
          "unilateral_faults": 0,
          "wins": 52
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 156,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 60,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "enabled",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "meituan/longcat-2.0",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 129,
          "model": "meituan/longcat-2.0",
          "point_rating_method": "sequential_elo",
          "public_id": "E-fe21773d3155f05f",
          "rated_matches": 156,
          "raw_elo_rating": 1094.481412085471,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "enabled",
          "repair_status": "first_pass",
          "score": 9.215953293432932,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 27
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 88,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 42,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "minimal",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "meta/muse-spark-1.2",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-08-13T16:58:34Z",
          "losses": 58,
          "model": "meta/muse-spark-1.2",
          "point_rating_method": "sequential_elo",
          "public_id": "E-5618329845b079c7",
          "rated_matches": 88,
          "raw_elo_rating": 1339.6829441858488,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "minimal",
          "repair_status": "first_pass",
          "score": 31.305998996116344,
          "uncertainty": 9.249894000318006,
          "unilateral_faults": 0,
          "wins": 30
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 92,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 43,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "meta/muse-spark-1.2",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-08-13T16:58:34Z",
          "losses": 22,
          "model": "meta/muse-spark-1.2",
          "point_rating_method": "sequential_elo",
          "public_id": "E-ab39e2e398a78370",
          "rated_matches": 92,
          "raw_elo_rating": 1713.3713882243446,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 66.56068088153548,
          "uncertainty": 8.09758473652126,
          "unilateral_faults": 0,
          "wins": 70
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 88,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 44,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "minimax/minimax-m3",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 51,
          "model": "minimax/minimax-m3",
          "point_rating_method": "sequential_elo",
          "public_id": "E-24e15c4d7490cdf3",
          "rated_matches": 88,
          "raw_elo_rating": 1367.2693290956158,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "none",
          "repair_status": "repaired",
          "score": 33.90216158577543,
          "uncertainty": 9.249894000318006,
          "unilateral_faults": 0,
          "wins": 37
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 120,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 56,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "enabled",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "minimax/minimax-m3",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 58,
          "model": "minimax/minimax-m3",
          "point_rating_method": "sequential_elo",
          "public_id": "E-4547f4cedca403f9",
          "rated_matches": 120,
          "raw_elo_rating": 1487.907737533893,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "enabled",
          "repair_status": "repaired",
          "score": 45.82355270808264,
          "uncertainty": 1.7045454545454586,
          "unilateral_faults": 0,
          "wins": 62
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 96,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 47,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "mistralai/mistral-medium-3-5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 75,
          "model": "mistralai/mistral-medium-3-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-d0d0df9d83b6e37e",
          "rated_matches": 96,
          "raw_elo_rating": 1213.7066599409454,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "first_pass",
          "score": 19.618422210437004,
          "uncertainty": 7.017308256680951,
          "unilateral_faults": 0,
          "wins": 21
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 116,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 55,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "enabled",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "moonshotai/kimi-k2.7-code",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 53,
          "model": "moonshotai/kimi-k2.7-code",
          "point_rating_method": "sequential_elo",
          "public_id": "E-d35e87ebfc251f60",
          "rated_matches": 116,
          "raw_elo_rating": 1503.7235320013426,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "enabled",
          "repair_status": "repaired",
          "score": 47.25397426838036,
          "uncertainty": 2.4750163521024238,
          "unilateral_faults": 0,
          "wins": 63
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 180,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 65,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "max",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "moonshotai/kimi-k3",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T14:00:00Z",
          "losses": 68,
          "model": "moonshotai/kimi-k3",
          "point_rating_method": "sequential_elo",
          "public_id": "E-1d1372c78963efdf",
          "rated_matches": 180,
          "raw_elo_rating": 1612.648077127973,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "max",
          "repair_status": "repaired",
          "score": 58.18702905042954,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 112
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 178,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 70,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "low",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "moonshotai/kimi-k3",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T14:00:00Z",
          "losses": 121,
          "model": "moonshotai/kimi-k3",
          "point_rating_method": "sequential_elo",
          "public_id": "E-4d8815930b656774",
          "rated_matches": 178,
          "raw_elo_rating": 1289.9508601455611,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "low",
          "repair_status": "first_pass",
          "score": 27.802313254046688,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 57
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 160,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 62,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "moonshotai/kimi-k3",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T14:00:00Z",
          "losses": 112,
          "model": "moonshotai/kimi-k3",
          "point_rating_method": "sequential_elo",
          "public_id": "E-55ef4536a723bcf7",
          "rated_matches": 160,
          "raw_elo_rating": 1302.1666353464232,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "first_pass",
          "score": 28.7988247426727,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 48
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 96,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 48,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "nex-agi/nex-n2-pro",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-11T17:22:09Z",
          "losses": 29,
          "model": "nex-agi/nex-n2-pro",
          "point_rating_method": "sequential_elo",
          "public_id": "E-1006c453b0c3a745",
          "rated_matches": 96,
          "raw_elo_rating": 1648.1717121399788,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "none",
          "repair_status": "repaired",
          "score": 60.50605278337446,
          "uncertainty": 7.017308256680951,
          "unilateral_faults": 0,
          "wins": 67
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 112,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 54,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "enabled",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "nex-agi/nex-n2-pro",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 59,
          "model": "nex-agi/nex-n2-pro",
          "point_rating_method": "sequential_elo",
          "public_id": "E-d1f432cda667f27f",
          "rated_matches": 112,
          "raw_elo_rating": 1454.1203052409805,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "enabled",
          "repair_status": "repaired",
          "score": 42.524739590732,
          "uncertainty": 3.286043419179858,
          "unilateral_faults": 0,
          "wins": 53
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 74,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 37,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "nvidia/nemotron-3-ultra-550b-a55b",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-03T18:15:00Z",
          "losses": 62,
          "model": "nvidia/nemotron-3-ultra-550b-a55b",
          "point_rating_method": "sequential_elo",
          "public_id": "E-0e1c7f89e1c19b69",
          "rated_matches": 74,
          "raw_elo_rating": 1144.8702182648058,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 12.615617756799654,
          "uncertainty": 13.985026918962571,
          "unilateral_faults": 0,
          "wins": 12
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 92,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 44,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "nvidia/nemotron-3-ultra-550b-a55b",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 72,
          "model": "nvidia/nemotron-3-ultra-550b-a55b",
          "point_rating_method": "sequential_elo",
          "public_id": "E-459f395cc0af6d2e",
          "rated_matches": 92,
          "raw_elo_rating": 1120.4180547333053,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "repaired",
          "score": 10.757672736091521,
          "uncertainty": 8.09758473652126,
          "unilateral_faults": 0,
          "wins": 20
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 161,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 59,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "o3",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-03T15:50:00Z",
          "losses": 87,
          "model": "o3",
          "point_rating_method": "sequential_elo",
          "public_id": "E-43c337fb7f5e535e",
          "rated_matches": 161,
          "raw_elo_rating": 1439.950195908931,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "first_pass",
          "score": 41.77484599142675,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 74
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 155,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 59,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "o3",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-03T15:45:00Z",
          "losses": 84,
          "model": "o3",
          "point_rating_method": "sequential_elo",
          "public_id": "E-541cee4461c65fcb",
          "rated_matches": 155,
          "raw_elo_rating": 1498.0682698361927,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "first_pass",
          "score": 47.18801426535529,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 71
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 166,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 62,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "low",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "o3",
            "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-21T14:20:15Z",
          "losses": 80,
          "model": "o3",
          "point_rating_method": "sequential_elo",
          "public_id": "E-585aa996c86c4b8a",
          "rated_matches": 166,
          "raw_elo_rating": 1543.6832616568183,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "low",
          "repair_status": "first_pass",
          "score": 51.58180645988167,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 86
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 162,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 58,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "o3",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 74,
          "model": "o3",
          "point_rating_method": "sequential_elo",
          "public_id": "E-bc20ac8102f6a0ac",
          "rated_matches": 162,
          "raw_elo_rating": 1648.1552922799856,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "first_pass",
          "score": 61.378173632216026,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 88
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 158,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 59,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "o3",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-03T16:00:00Z",
          "losses": 105,
          "model": "o3",
          "point_rating_method": "sequential_elo",
          "public_id": "E-ee95d01578313864",
          "rated_matches": 158,
          "raw_elo_rating": 1318.4051069389095,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "first_pass",
          "score": 30.308431325245213,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 53
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 106,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 53,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "o3",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 42,
          "model": "o3",
          "point_rating_method": "sequential_elo",
          "public_id": "E-f1e3e54a3d40556f",
          "rated_matches": 106,
          "raw_elo_rating": 1636.9247706055485,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 59.630586714276724,
          "uncertainty": 4.586824452283178,
          "unilateral_faults": 0,
          "wins": 64
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 96,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 47,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "openai/gpt-oss-120b",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 65,
          "model": "openai/gpt-oss-120b",
          "point_rating_method": "sequential_elo",
          "public_id": "E-29bc7f4fdf0f7b14",
          "rated_matches": 96,
          "raw_elo_rating": 1426.4652985743849,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "repaired",
          "score": 39.64119866533117,
          "uncertainty": 7.017308256680951,
          "unilateral_faults": 0,
          "wins": 31
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 168,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 64,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "low",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "openai/gpt-oss-120b",
            "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-21T14:20:15Z",
          "losses": 142,
          "model": "openai/gpt-oss-120b",
          "point_rating_method": "sequential_elo",
          "public_id": "E-759d747bb732d949",
          "rated_matches": 168,
          "raw_elo_rating": 1108.1862556209687,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "low",
          "repair_status": "first_pass",
          "score": 10.614346337124728,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 26
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 109,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 49,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "poolside/laguna-s-2.1",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 63,
          "model": "poolside/laguna-s-2.1",
          "point_rating_method": "sequential_elo",
          "public_id": "E-069a963abdd14cdf",
          "rated_matches": 100,
          "raw_elo_rating": 1464.3369924640717,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 43.28176596870082,
          "uncertainty": 6.001859510499461,
          "unilateral_faults": 0,
          "wins": 37
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 102,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 51,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "poolside/laguna-s-2.1",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 50,
          "model": "poolside/laguna-s-2.1",
          "point_rating_method": "sequential_elo",
          "public_id": "E-d8e68d23876f6d21",
          "rated_matches": 102,
          "raw_elo_rating": 1623.6832947172982,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 58.31443671515227,
          "uncertainty": 5.516463908214657,
          "unilateral_faults": 0,
          "wins": 52
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 90,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 45,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "qwen/qwen3.7-max",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 32,
          "model": "qwen/qwen3.7-max",
          "point_rating_method": "sequential_elo",
          "public_id": "E-3142a09c7f192060",
          "rated_matches": 90,
          "raw_elo_rating": 1703.2609653449783,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 65.56652347725021,
          "uncertainty": 8.664241836095918,
          "unilateral_faults": 0,
          "wins": 58
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 86,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 43,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "enabled",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "qwen/qwen3.7-max",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 21,
          "model": "qwen/qwen3.7-max",
          "point_rating_method": "sequential_elo",
          "public_id": "E-59c7745eb1e91d63",
          "rated_matches": 86,
          "raw_elo_rating": 1780.9950468049765,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "enabled",
          "repair_status": "repaired",
          "score": 72.79240290081826,
          "uncertainty": 9.855626741889738,
          "unilateral_faults": 0,
          "wins": 65
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 86,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 42,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "qwen/qwen3.7-plus",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 66,
          "model": "qwen/qwen3.7-plus",
          "point_rating_method": "sequential_elo",
          "public_id": "E-737a66790985a5e6",
          "rated_matches": 84,
          "raw_elo_rating": 1053.14781558953,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 4.247286587507169,
          "uncertainty": 10.482614454664043,
          "unilateral_faults": 2,
          "wins": 18
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 114,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 55,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "enabled",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "qwen/qwen3.7-plus",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 57,
          "model": "qwen/qwen3.7-plus",
          "point_rating_method": "sequential_elo",
          "public_id": "E-9d091700cb41ece2",
          "rated_matches": 114,
          "raw_elo_rating": 1450.7149866418183,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "enabled",
          "repair_status": "repaired",
          "score": 42.23519271244378,
          "uncertainty": 2.875240412015687,
          "unilateral_faults": 0,
          "wins": 57
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 20,
          "capped_draws": 0,
          "coverage_status": "under_covered",
          "distinct_rated_opponents": 8,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "xhigh",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "qwen/qwen3.8-max",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 0,
          "model": "qwen/qwen3.8-max",
          "point_rating_method": "sequential_elo",
          "public_id": "E-1c3cd7cd7b39b7ff",
          "rated_matches": 20,
          "raw_elo_rating": 1746.3008626110957,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "xhigh",
          "repair_status": "first_pass",
          "score": 65.34857672458816,
          "uncertainty": 65.3589451179962,
          "unilateral_faults": 0,
          "wins": 20
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 18,
          "capped_draws": 0,
          "coverage_status": "under_covered",
          "distinct_rated_opponents": 10,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "qwen/qwen3.8-max",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 10,
          "model": "qwen/qwen3.8-max",
          "point_rating_method": "sequential_elo",
          "public_id": "E-1f83b2062e021657",
          "rated_matches": 18,
          "raw_elo_rating": 1452.2408415859013,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 37.2529709637503,
          "uncertainty": 70.95786693528086,
          "unilateral_faults": 0,
          "wins": 8
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 19,
          "capped_draws": 0,
          "coverage_status": "under_covered",
          "distinct_rated_opponents": 10,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "minimal",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "qwen/qwen3.8-max",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 7,
          "model": "qwen/qwen3.8-max",
          "point_rating_method": "sequential_elo",
          "public_id": "E-9060604c6d76c81b",
          "rated_matches": 19,
          "raw_elo_rating": 1558.924963586655,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "minimal",
          "repair_status": "first_pass",
          "score": 47.51171651636437,
          "uncertainty": 68.05339887498948,
          "unilateral_faults": 0,
          "wins": 12
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 16,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 8,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "max",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "stealth/ox-alpha",
            "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-08-22T00:27:26Z",
          "losses": 4,
          "model": "stealth/ox-alpha",
          "point_rating_method": "sequential_elo",
          "public_id": "E-27243ca72bb71e47",
          "rated_matches": 16,
          "raw_elo_rating": 1601.6512786766596,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "max",
          "repair_status": "first_pass",
          "score": 50.82014332989595,
          "uncertainty": 77.5178125181665,
          "unilateral_faults": 0,
          "wins": 12
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 16,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 8,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "max",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "stealth/ox-alpha",
            "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-08-22T00:27:26Z",
          "losses": 5,
          "model": "stealth/ox-alpha",
          "point_rating_method": "sequential_elo",
          "public_id": "E-6160aff1d9ab7bd7",
          "rated_matches": 16,
          "raw_elo_rating": 1559.7727172879754,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "max",
          "repair_status": "first_pass",
          "score": 46.878939915904965,
          "uncertainty": 77.5178125181665,
          "unilateral_faults": 0,
          "wins": 11
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 16,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 8,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "stealth/ox-alpha",
            "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-08-22T00:27:26Z",
          "losses": 16,
          "model": "stealth/ox-alpha",
          "point_rating_method": "sequential_elo",
          "public_id": "E-90df0bc1145d0335",
          "rated_matches": 16,
          "raw_elo_rating": 1311.2344400533552,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "first_pass",
          "score": 23.488931418402004,
          "uncertainty": 77.5178125181665,
          "unilateral_faults": 0,
          "wins": 0
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 16,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 8,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "stealth/ox-alpha",
            "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-08-22T00:27:26Z",
          "losses": 12,
          "model": "stealth/ox-alpha",
          "point_rating_method": "sequential_elo",
          "public_id": "E-9cc97e533afb41b3",
          "rated_matches": 16,
          "raw_elo_rating": 1410.7754751963084,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "first_pass",
          "score": 32.85676676251696,
          "uncertainty": 77.5178125181665,
          "unilateral_faults": 0,
          "wins": 4
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 16,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 8,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "max",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "stealth/ox-alpha",
            "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-08-22T00:27:26Z",
          "losses": 8,
          "model": "stealth/ox-alpha",
          "point_rating_method": "sequential_elo",
          "public_id": "E-9f68949b5725fa77",
          "rated_matches": 16,
          "raw_elo_rating": 1512.3951665763,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "max",
          "repair_status": "first_pass",
          "score": 42.420225040808035,
          "uncertainty": 77.5178125181665,
          "unilateral_faults": 0,
          "wins": 8
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 16,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 8,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "stealth/ox-alpha",
            "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-08-22T00:27:26Z",
          "losses": 0,
          "model": "stealth/ox-alpha",
          "point_rating_method": "sequential_elo",
          "public_id": "E-ae808d1219edf709",
          "rated_matches": 16,
          "raw_elo_rating": 1678.926051188307,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "first_pass",
          "score": 58.09249431663672,
          "uncertainty": 77.5178125181665,
          "unilateral_faults": 0,
          "wins": 16
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 16,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 8,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "low",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "stealth/ox-alpha",
            "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-08-22T00:27:26Z",
          "losses": 4,
          "model": "stealth/ox-alpha",
          "point_rating_method": "sequential_elo",
          "public_id": "E-b7e03d205460428f",
          "rated_matches": 16,
          "raw_elo_rating": 1595.1872718968311,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "low",
          "repair_status": "first_pass",
          "score": 50.21181379936904,
          "uncertainty": 77.5178125181665,
          "unilateral_faults": 0,
          "wins": 12
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 16,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 8,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "low",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "stealth/ox-alpha",
            "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-08-22T00:27:26Z",
          "losses": 10,
          "model": "stealth/ox-alpha",
          "point_rating_method": "sequential_elo",
          "public_id": "E-c2beebe255c607a1",
          "rated_matches": 16,
          "raw_elo_rating": 1445.8719739585094,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "low",
          "repair_status": "first_pass",
          "score": 36.15970831910282,
          "uncertainty": 77.5178125181665,
          "unilateral_faults": 0,
          "wins": 6
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 16,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 8,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "low",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "stealth/ox-alpha",
            "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-08-22T00:27:26Z",
          "losses": 13,
          "model": "stealth/ox-alpha",
          "point_rating_method": "sequential_elo",
          "public_id": "E-f9e2fbd96bb7a98d",
          "rated_matches": 16,
          "raw_elo_rating": 1384.185625165754,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "low",
          "repair_status": "first_pass",
          "score": 30.354388355930954,
          "uncertainty": 77.5178125181665,
          "unilateral_faults": 0,
          "wins": 3
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 178,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 68,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "low",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "stepfun/step-3.7-flash",
            "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-21T14:20:15Z",
          "losses": 109,
          "model": "stepfun/step-3.7-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-1140a7c92290e8f4",
          "rated_matches": 178,
          "raw_elo_rating": 1378.7192000023038,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "low",
          "repair_status": "repaired",
          "score": 36.156327157500364,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 69
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 101,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 50,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "stepfun/step-3.7-flash",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 66,
          "model": "stepfun/step-3.7-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-6a5e44fe2dde4257",
          "rated_matches": 101,
          "raw_elo_rating": 1349.1712838775788,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "repaired",
          "score": 32.46189477313855,
          "uncertainty": 5.757377148833722,
          "unilateral_faults": 0,
          "wins": 35
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 104,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 50,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "tencent/hy3-preview",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 67,
          "model": "tencent/hy3-preview",
          "point_rating_method": "sequential_elo",
          "public_id": "E-dfed1e345a939bcd",
          "rated_matches": 104,
          "raw_elo_rating": 1276.1948853703204,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "first_pass",
          "score": 25.647698335291103,
          "uncertainty": 5.045003647426665,
          "unilateral_faults": 0,
          "wins": 37
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 104,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 51,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "thinkingmachines/inkling",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 56,
          "model": "thinkingmachines/inkling",
          "point_rating_method": "sequential_elo",
          "public_id": "E-062d41f517db2ccb",
          "rated_matches": 104,
          "raw_elo_rating": 1320.0660988276552,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 29.776430806523866,
          "uncertainty": 5.045003647426665,
          "unilateral_faults": 0,
          "wins": 48
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 174,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 66,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "max",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "thinkingmachines/inkling",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 129,
          "model": "thinkingmachines/inkling",
          "point_rating_method": "sequential_elo",
          "public_id": "E-38e756fc6f3a2db6",
          "rated_matches": 174,
          "raw_elo_rating": 1268.3605173911951,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "max",
          "repair_status": "repaired",
          "score": 25.73846555139435,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 45
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 156,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 61,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "thinkingmachines/inkling",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 139,
          "model": "thinkingmachines/inkling",
          "point_rating_method": "sequential_elo",
          "public_id": "E-b9ceec0ad4a1b9a4",
          "rated_matches": 156,
          "raw_elo_rating": 1082.0671538643896,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 8.04764389452622,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 17
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 16,
          "capped_draws": 0,
          "coverage_status": "under_covered",
          "distinct_rated_opponents": 9,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "max",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "thinkingmachines/inkling-small",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 15,
          "model": "thinkingmachines/inkling-small",
          "point_rating_method": "sequential_elo",
          "public_id": "E-516d381904063142",
          "rated_matches": 16,
          "raw_elo_rating": 1304.7852176135736,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "max",
          "repair_status": "first_pass",
          "score": 22.881993246353847,
          "uncertainty": 77.5178125181665,
          "unilateral_faults": 0,
          "wins": 1
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 19,
          "capped_draws": 0,
          "coverage_status": "under_covered",
          "distinct_rated_opponents": 9,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "thinkingmachines/inkling-small",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 8,
          "model": "thinkingmachines/inkling-small",
          "point_rating_method": "sequential_elo",
          "public_id": "E-b205e1d25c695262",
          "rated_matches": 19,
          "raw_elo_rating": 1542.484591986778,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 45.96450843356181,
          "uncertainty": 68.05339887498948,
          "unilateral_faults": 0,
          "wins": 11
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 20,
          "capped_draws": 0,
          "coverage_status": "under_covered",
          "distinct_rated_opponents": 11,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "thinkingmachines/inkling-small",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 14,
          "model": "thinkingmachines/inkling-small",
          "point_rating_method": "sequential_elo",
          "public_id": "E-f330739aca81e515",
          "rated_matches": 20,
          "raw_elo_rating": 1405.8173258582663,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "repaired",
          "score": 33.305573503838346,
          "uncertainty": 65.3589451179962,
          "unilateral_faults": 0,
          "wins": 6
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 146,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 57,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "low",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "x-ai/grok-4.5",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T14:00:00Z",
          "losses": 33,
          "model": "x-ai/grok-4.5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-1d206565b78f3121",
          "rated_matches": 146,
          "raw_elo_rating": 1761.1992839087297,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "low",
          "repair_status": "first_pass",
          "score": 71.8604564523625,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 113
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 166,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 66,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "x-ai/grok-4.5",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T14:00:00Z",
          "losses": 62,
          "model": "x-ai/grok-4.5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-436a3933a93e10cd",
          "rated_matches": 166,
          "raw_elo_rating": 1657.3711692973993,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "first_pass",
          "score": 62.28100802900767,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 104
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 112,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 56,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "x-ai/grok-4.5",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T14:00:00Z",
          "losses": 47,
          "model": "x-ai/grok-4.5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-e58f3df122cf1d29",
          "rated_matches": 112,
          "raw_elo_rating": 1656.3784608491428,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "repaired",
          "score": 61.55931257885285,
          "uncertainty": 3.286043419179858,
          "unilateral_faults": 0,
          "wins": 65
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 106,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 50,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "enabled",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "x-ai/grok-build-0.1",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 73,
          "model": "x-ai/grok-build-0.1",
          "point_rating_method": "sequential_elo",
          "public_id": "E-37ae0129627ee16f",
          "rated_matches": 106,
          "raw_elo_rating": 1249.6710367295523,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "enabled",
          "repair_status": "repaired",
          "score": 23.186026838702013,
          "uncertainty": 4.586824452283178,
          "unilateral_faults": 0,
          "wins": 33
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 88,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 43,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "xiaomi/mimo-v2.5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 59,
          "model": "xiaomi/mimo-v2.5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-0984b025e9005f5b",
          "rated_matches": 86,
          "raw_elo_rating": 1137.1745265340696,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "none",
          "repair_status": "repaired",
          "score": 12.202269229827921,
          "uncertainty": 9.855626741889738,
          "unilateral_faults": 2,
          "wins": 27
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 96,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 44,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "xiaomi/mimo-v2.5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-01T00:15:48Z",
          "losses": 45,
          "model": "xiaomi/mimo-v2.5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-345a5b25cbac7f3b",
          "rated_matches": 96,
          "raw_elo_rating": 1536.730322602996,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 50.01827167679295,
          "uncertainty": 7.017308256680951,
          "unilateral_faults": 0,
          "wins": 51
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 88,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 44,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "xiaomi/mimo-v2.5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-01T00:15:48Z",
          "losses": 40,
          "model": "xiaomi/mimo-v2.5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-47d67dcf0077af42",
          "rated_matches": 88,
          "raw_elo_rating": 1496.523954140653,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 46.066351390998115,
          "uncertainty": 9.249894000318006,
          "unilateral_faults": 0,
          "wins": 48
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 104,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 50,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "enabled",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "xiaomi/mimo-v2.5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 58,
          "model": "xiaomi/mimo-v2.5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-fa1a93f7e4d57000",
          "rated_matches": 104,
          "raw_elo_rating": 1324.660786450052,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "enabled",
          "repair_status": "repaired",
          "score": 30.208838175428983,
          "uncertainty": 5.045003647426665,
          "unilateral_faults": 0,
          "wins": 46
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 120,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 59,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "enabled",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "xiaomi/mimo-v2.5-pro",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 62,
          "model": "xiaomi/mimo-v2.5-pro",
          "point_rating_method": "sequential_elo",
          "public_id": "E-3b160130ae038271",
          "rated_matches": 120,
          "raw_elo_rating": 1467.492796093447,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "enabled",
          "repair_status": "repaired",
          "score": 43.90229671853825,
          "uncertainty": 1.7045454545454586,
          "unilateral_faults": 0,
          "wins": 58
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 94,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 47,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "xiaomi/mimo-v2.5-pro",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 37,
          "model": "xiaomi/mimo-v2.5-pro",
          "point_rating_method": "sequential_elo",
          "public_id": "E-83580d03385c6759",
          "rated_matches": 94,
          "raw_elo_rating": 1539.1060983283344,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 50.20183268472181,
          "uncertainty": 7.54891760425771,
          "unilateral_faults": 0,
          "wins": 57
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 74,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 37,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "z-ai/glm-5.2",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-11T14:00:45Z",
          "losses": 44,
          "model": "z-ai/glm-5.2",
          "point_rating_method": "sequential_elo",
          "public_id": "E-62e8714f035ebc68",
          "rated_matches": 74,
          "raw_elo_rating": 1404.082365452216,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 37.01014721451399,
          "uncertainty": 13.985026918962571,
          "unilateral_faults": 0,
          "wins": 30
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 78,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 39,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "z-ai/glm-5.2",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 39,
          "model": "z-ai/glm-5.2",
          "point_rating_method": "sequential_elo",
          "public_id": "E-e31f275ab7ef3741",
          "rated_matches": 78,
          "raw_elo_rating": 1634.8958569158183,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 58.843545195365074,
          "uncertainty": 12.5043950463012,
          "unilateral_faults": 0,
          "wins": 39
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 82,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 41,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "z-ai/glm-5.2",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-11T17:22:09Z",
          "losses": 34,
          "model": "z-ai/glm-5.2",
          "point_rating_method": "sequential_elo",
          "public_id": "E-ecd98326faa92bf4",
          "rated_matches": 82,
          "raw_elo_rating": 1539.4625749629602,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "repaired",
          "score": 49.96560708699275,
          "uncertainty": 11.132129994845172,
          "unilateral_faults": 0,
          "wins": 48
        }
      ],
      "GB2-08": [
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 102,
          "capped_draws": 1,
          "coverage_status": "rated",
          "distinct_rated_opponents": 48,
          "draws": 1,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "xhigh",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-fable-5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 4,
          "model": "claude-fable-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-12891afa894223fd",
          "rated_matches": 102,
          "raw_elo_rating": 2070.226734381098,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "xhigh",
          "repair_status": "repaired",
          "score": 100.0,
          "uncertainty": 5.516463908214657,
          "unilateral_faults": 0,
          "wins": 97
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 92,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 45,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-fable-5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 12,
          "model": "claude-fable-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-9ccf296d44d35675",
          "rated_matches": 92,
          "raw_elo_rating": 1817.575241405041,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 74.2473959519865,
          "uncertainty": 8.09758473652126,
          "unilateral_faults": 0,
          "wins": 80
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 90,
          "capped_draws": 6,
          "coverage_status": "rated",
          "distinct_rated_opponents": 45,
          "draws": 6,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-opus-4-5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "omitted",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 19,
          "model": "claude-opus-4-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-01b57d5e6655f927",
          "rated_matches": 90,
          "raw_elo_rating": 1770.4607839572238,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "omitted",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 69.43814796420975,
          "uncertainty": 8.664241836095918,
          "unilateral_faults": 0,
          "wins": 65
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 0,
          "capped_draws": 0,
          "coverage_status": "pending",
          "distinct_rated_opponents": 0,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "legacy_shared_thinking_budget",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-opus-4-5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "budget",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 0,
          "model": "claude-opus-4-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-355427eb0d526f34",
          "rated_matches": 0,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "budget",
          "reasoning_setting": "legacy_shared_thinking_budget",
          "repair_status": "first_pass",
          "unilateral_faults": 0,
          "wins": 0
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 0,
          "capped_draws": 0,
          "coverage_status": "pending",
          "distinct_rated_opponents": 0,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "legacy_shared_thinking_budget",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-opus-4-5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "budget",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 0,
          "model": "claude-opus-4-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-6a0c04b4335bfea0",
          "rated_matches": 0,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "budget",
          "reasoning_setting": "legacy_shared_thinking_budget",
          "repair_status": "first_pass",
          "unilateral_faults": 0,
          "wins": 0
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 176,
          "capped_draws": 2,
          "coverage_status": "rated",
          "distinct_rated_opponents": 73,
          "draws": 2,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-opus-4-5",
            "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 28,
          "model": "claude-opus-4-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-72233463ddce5549",
          "rated_matches": 176,
          "raw_elo_rating": 1884.3566176372763,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 82.15300774815739,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 146
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 186,
          "capped_draws": 99,
          "coverage_status": "rated",
          "distinct_rated_opponents": 65,
          "draws": 99,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-opus-4-5",
            "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 70,
          "model": "claude-opus-4-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-877eec51affacb3a",
          "rated_matches": 186,
          "raw_elo_rating": 1346.2739670506865,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "first_pass",
          "score": 27.83360360167963,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 17
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 100,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 47,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "xhigh",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-opus-4-8",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-03T17:20:00Z",
          "losses": 23,
          "model": "claude-opus-4-8",
          "point_rating_method": "sequential_elo",
          "public_id": "E-22dc6fe5ae5fb8b1",
          "rated_matches": 100,
          "raw_elo_rating": 1792.3813910887834,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "xhigh",
          "repair_status": "first_pass",
          "score": 71.86972819787296,
          "uncertainty": 6.001859510499461,
          "unilateral_faults": 0,
          "wins": 77
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 110,
          "capped_draws": 84,
          "coverage_status": "rated",
          "distinct_rated_opponents": 54,
          "draws": 84,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-opus-4-8",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 21,
          "model": "claude-opus-4-8",
          "point_rating_method": "sequential_elo",
          "public_id": "E-c2dade0b97891d8a",
          "rated_matches": 110,
          "raw_elo_rating": 1395.7974788159802,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 31.959425881493154,
          "uncertainty": 3.707899787624953,
          "unilateral_faults": 0,
          "wins": 5
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 90,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 45,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-opus-4-8",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "omitted",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 25,
          "model": "claude-opus-4-8",
          "point_rating_method": "sequential_elo",
          "public_id": "E-c9d7578e8375d994",
          "rated_matches": 90,
          "raw_elo_rating": 1773.8635077665217,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "omitted",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 69.78217372191577,
          "uncertainty": 8.664241836095918,
          "unilateral_faults": 0,
          "wins": 65
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 102,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 51,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-opus-5",
            "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-25T10:50:00Z",
          "losses": 20,
          "model": "claude-opus-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-35a5bf9b35d5e1e8",
          "rated_matches": 102,
          "raw_elo_rating": 1862.4936313700762,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 78.99754956052814,
          "uncertainty": 5.516463908214657,
          "unilateral_faults": 0,
          "wins": 82
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 162,
          "capped_draws": 16,
          "coverage_status": "rated",
          "distinct_rated_opponents": 62,
          "draws": 16,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-opus-5",
            "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-25T10:50:00Z",
          "losses": 20,
          "model": "claude-opus-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-43cc1c89fa5720b3",
          "rated_matches": 162,
          "raw_elo_rating": 1842.3354939772314,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 77.77669137324924,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 126
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 114,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 57,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-opus-5",
            "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-25T10:50:00Z",
          "losses": 37,
          "model": "claude-opus-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-5a7942274854aaa6",
          "rated_matches": 114,
          "raw_elo_rating": 1628.0363266293714,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 55.506829401848854,
          "uncertainty": 2.875240412015687,
          "unilateral_faults": 0,
          "wins": 77
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 86,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 37,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "xhigh",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-opus-5",
            "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-25T15:48:01Z",
          "losses": 13,
          "model": "claude-opus-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-a40851c4f03704e5",
          "rated_matches": 86,
          "raw_elo_rating": 1903.459258801908,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "xhigh",
          "repair_status": "first_pass",
          "score": 82.78833738661038,
          "uncertainty": 9.855626741889738,
          "unilateral_faults": 0,
          "wins": 73
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 104,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 52,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-opus-5",
            "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-25T10:50:00Z",
          "losses": 8,
          "model": "claude-opus-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-e73b6fb78880341d",
          "rated_matches": 104,
          "raw_elo_rating": 1990.1371275012355,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 91.94082927402685,
          "uncertainty": 5.045003647426665,
          "unilateral_faults": 0,
          "wins": 96
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 88,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 40,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "xhigh",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-opus-5",
            "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-25T15:48:01Z",
          "losses": 26,
          "model": "claude-opus-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-f5914ca845403384",
          "rated_matches": 88,
          "raw_elo_rating": 1692.3978760053656,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "xhigh",
          "repair_status": "first_pass",
          "score": 61.498380849791204,
          "uncertainty": 9.249894000318006,
          "unilateral_faults": 0,
          "wins": 62
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 88,
          "capped_draws": 52,
          "coverage_status": "rated",
          "distinct_rated_opponents": 42,
          "draws": 52,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-sonnet-5",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 29,
          "model": "claude-sonnet-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-01c56a1fc7407264",
          "rated_matches": 88,
          "raw_elo_rating": 1384.3413005388531,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 30.352921291303954,
          "uncertainty": 9.249894000318006,
          "unilateral_faults": 0,
          "wins": 7
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 112,
          "capped_draws": 85,
          "coverage_status": "rated",
          "distinct_rated_opponents": 56,
          "draws": 85,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-sonnet-5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 20,
          "model": "claude-sonnet-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-130fb40b1c7a4d39",
          "rated_matches": 112,
          "raw_elo_rating": 1407.0267536166316,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 33.12886059328138,
          "uncertainty": 3.286043419179858,
          "unilateral_faults": 0,
          "wins": 7
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 102,
          "capped_draws": 55,
          "coverage_status": "rated",
          "distinct_rated_opponents": 49,
          "draws": 55,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "xhigh",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-sonnet-5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-03T16:50:00Z",
          "losses": 38,
          "model": "claude-sonnet-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-b5805acb90227d50",
          "rated_matches": 102,
          "raw_elo_rating": 1427.5092315776758,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "xhigh",
          "repair_status": "first_pass",
          "score": 35.019299747841444,
          "uncertainty": 5.516463908214657,
          "unilateral_faults": 0,
          "wins": 9
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 86,
          "capped_draws": 34,
          "coverage_status": "rated",
          "distinct_rated_opponents": 42,
          "draws": 34,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-sonnet-5",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 27,
          "model": "claude-sonnet-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-c2e7d7e507756f84",
          "rated_matches": 86,
          "raw_elo_rating": 1482.505798798824,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 40.22865839038472,
          "uncertainty": 9.855626741889738,
          "unilateral_faults": 0,
          "wins": 25
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 116,
          "capped_draws": 108,
          "coverage_status": "rated",
          "distinct_rated_opponents": 56,
          "draws": 108,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-sonnet-5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 5,
          "model": "claude-sonnet-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-cf0ed4bbe4aaadd7",
          "rated_matches": 116,
          "raw_elo_rating": 1375.919697911772,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 30.049440212697277,
          "uncertainty": 2.4750163521024238,
          "unilateral_faults": 0,
          "wins": 3
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 90,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 42,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "xhigh",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-sonnet-5",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 13,
          "model": "claude-sonnet-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-df0550ce48a0b895",
          "rated_matches": 90,
          "raw_elo_rating": 1884.7508193563601,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "xhigh",
          "repair_status": "first_pass",
          "score": 80.99321920419641,
          "uncertainty": 8.664241836095918,
          "unilateral_faults": 0,
          "wins": 77
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 120,
          "capped_draws": 96,
          "coverage_status": "rated",
          "distinct_rated_opponents": 53,
          "draws": 96,
          "evaluated_setting_identity": {
            "canonical_provider_route": "unknown_legacy",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "cohere/north-mini-code:free",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-11T17:22:09Z",
          "losses": 20,
          "model": "cohere/north-mini-code",
          "point_rating_method": "sequential_elo",
          "public_id": "E-c36a98e057c264eb",
          "rated_matches": 120,
          "raw_elo_rating": 1402.3296396091612,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 32.78188345286514,
          "uncertainty": 1.7045454545454586,
          "unilateral_faults": 0,
          "wins": 4
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 68,
          "capped_draws": 50,
          "coverage_status": "rated",
          "distinct_rated_opponents": 34,
          "draws": 50,
          "evaluated_setting_identity": {
            "canonical_provider_route": "unknown_legacy",
            "effective_request_value": "enabled",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "cohere/north-mini-code:free",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 18,
          "model": "cohere/north-mini-code",
          "point_rating_method": "sequential_elo",
          "public_id": "E-efd7b75d5cd3b538",
          "rated_matches": 68,
          "raw_elo_rating": 1381.6595847116837,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "enabled",
          "repair_status": "first_pass",
          "score": 29.500001613253012,
          "uncertainty": 16.4429265428846,
          "unilateral_faults": 0,
          "wins": 0
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 112,
          "capped_draws": 88,
          "coverage_status": "rated",
          "distinct_rated_opponents": 54,
          "draws": 88,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "deepseek/deepseek-v4-flash",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 18,
          "model": "deepseek/deepseek-v4-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-4375cf96eeb624e2",
          "rated_matches": 112,
          "raw_elo_rating": 1404.0594040768221,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "repaired",
          "score": 32.82885250240368,
          "uncertainty": 3.286043419179858,
          "unilateral_faults": 0,
          "wins": 6
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 80,
          "capped_draws": 71,
          "coverage_status": "rated",
          "distinct_rated_opponents": 40,
          "draws": 71,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "deepseek/deepseek-v4-flash",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T06:10:40Z",
          "losses": 7,
          "model": "deepseek/deepseek-v4-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-43aba68125a9abc5",
          "rated_matches": 80,
          "raw_elo_rating": 1423.616337969348,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 34.11703924691805,
          "uncertainty": 11.805555555555554,
          "unilateral_faults": 0,
          "wins": 2
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 108,
          "capped_draws": 77,
          "coverage_status": "rated",
          "distinct_rated_opponents": 54,
          "draws": 77,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "xhigh",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "deepseek/deepseek-v4-flash",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 29,
          "model": "deepseek/deepseek-v4-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-a7310645c3b96434",
          "rated_matches": 108,
          "raw_elo_rating": 1398.1860928220167,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "xhigh",
          "repair_status": "repaired",
          "score": 32.16586642400081,
          "uncertainty": 4.1413142610575715,
          "unilateral_faults": 0,
          "wins": 2
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 84,
          "capped_draws": 73,
          "coverage_status": "rated",
          "distinct_rated_opponents": 42,
          "draws": 73,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "deepseek/deepseek-v4-flash",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-01T00:15:48Z",
          "losses": 9,
          "model": "deepseek/deepseek-v4-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-d28ef17ff6995c62",
          "rated_matches": 84,
          "raw_elo_rating": 1364.473428735264,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "repaired",
          "score": 28.244513402803264,
          "uncertainty": 10.482614454664043,
          "unilateral_faults": 0,
          "wins": 2
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 94,
          "capped_draws": 65,
          "coverage_status": "rated",
          "distinct_rated_opponents": 44,
          "draws": 65,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "xhigh",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "deepseek/deepseek-v4-pro",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 25,
          "model": "deepseek/deepseek-v4-pro",
          "point_rating_method": "sequential_elo",
          "public_id": "E-3a5b5c4507a989d3",
          "rated_matches": 94,
          "raw_elo_rating": 1387.905101445435,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "xhigh",
          "repair_status": "repaired",
          "score": 30.850811557145292,
          "uncertainty": 7.54891760425771,
          "unilateral_faults": 0,
          "wins": 4
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 108,
          "capped_draws": 82,
          "coverage_status": "rated",
          "distinct_rated_opponents": 53,
          "draws": 82,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "deepseek/deepseek-v4-pro",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 17,
          "model": "deepseek/deepseek-v4-pro",
          "point_rating_method": "sequential_elo",
          "public_id": "E-c296a7abab6975d7",
          "rated_matches": 108,
          "raw_elo_rating": 1516.1908415956534,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 44.09650651851254,
          "uncertainty": 4.1413142610575715,
          "unilateral_faults": 0,
          "wins": 9
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 106,
          "capped_draws": 72,
          "coverage_status": "rated",
          "distinct_rated_opponents": 51,
          "draws": 72,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "google/gemini-3.1-flash-lite",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 28,
          "model": "google/gemini-3.1-flash-lite",
          "point_rating_method": "sequential_elo",
          "public_id": "E-b335c9f92035f80b",
          "rated_matches": 106,
          "raw_elo_rating": 1381.0312376325182,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "repaired",
          "score": 30.395424278997872,
          "uncertainty": 4.586824452283178,
          "unilateral_faults": 0,
          "wins": 6
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 132,
          "capped_draws": 40,
          "coverage_status": "rated",
          "distinct_rated_opponents": 66,
          "draws": 40,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "google/gemini-3.1-flash-lite",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 51,
          "model": "google/gemini-3.1-flash-lite",
          "point_rating_method": "sequential_elo",
          "public_id": "E-cc6fb78c96472032",
          "rated_matches": 132,
          "raw_elo_rating": 1434.8578660442124,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 36.2403624207267,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 41
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 0,
          "capped_draws": 0,
          "coverage_status": "pending",
          "distinct_rated_opponents": 0,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "low",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "google/gemini-3.5-flash",
            "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-21T14:20:15Z",
          "losses": 0,
          "model": "google/gemini-3.5-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-5aa593158b0d8b3a",
          "rated_matches": 0,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "low",
          "repair_status": "first_pass",
          "unilateral_faults": 0,
          "wins": 0
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 90,
          "capped_draws": 68,
          "coverage_status": "rated",
          "distinct_rated_opponents": 45,
          "draws": 68,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "google/gemini-3.5-flash",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 22,
          "model": "google/gemini-3.5-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-bd0bbefbbd252fc5",
          "rated_matches": 90,
          "raw_elo_rating": 1332.5013086471351,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "repaired",
          "score": 25.159108940712393,
          "uncertainty": 8.664241836095918,
          "unilateral_faults": 0,
          "wins": 0
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 96,
          "capped_draws": 62,
          "coverage_status": "rated",
          "distinct_rated_opponents": 48,
          "draws": 62,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "google/gemini-3.5-flash",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 34,
          "model": "google/gemini-3.5-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-fa332e578ae97122",
          "rated_matches": 96,
          "raw_elo_rating": 1296.1001435676862,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "repaired",
          "score": 21.612048110556422,
          "uncertainty": 7.017308256680951,
          "unilateral_faults": 0,
          "wins": 0
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 172,
          "capped_draws": 118,
          "coverage_status": "rated",
          "distinct_rated_opponents": 64,
          "draws": 118,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "minimal",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "google/gemini-3.5-flash-lite",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 47,
          "model": "google/gemini-3.5-flash-lite",
          "point_rating_method": "sequential_elo",
          "public_id": "E-284d554eca16e6f6",
          "rated_matches": 172,
          "raw_elo_rating": 1353.7438529638846,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "minimal",
          "repair_status": "first_pass",
          "score": 28.47149773278937,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 7
        },
        {
          "admitted_plugin_count": 2,
          "attempted_matches": 170,
          "capped_draws": 102,
          "coverage_status": "rated",
          "distinct_rated_opponents": 62,
          "draws": 102,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "google/gemini-3.5-flash-lite",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 61,
          "model": "google/gemini-3.5-flash-lite",
          "point_rating_method": "sequential_elo",
          "public_id": "E-2a14d2f80ade1bda",
          "rated_matches": 170,
          "raw_elo_rating": 1329.5503292837363,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "first_pass",
          "score": 26.007530314351136,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 7
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 164,
          "capped_draws": 113,
          "coverage_status": "rated",
          "distinct_rated_opponents": 62,
          "draws": 113,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "google/gemini-3.5-flash-lite",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 44,
          "model": "google/gemini-3.5-flash-lite",
          "point_rating_method": "sequential_elo",
          "public_id": "E-2f2aa5b1beafd6e6",
          "rated_matches": 164,
          "raw_elo_rating": 1329.6384448839742,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 25.960711751224267,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 7
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 156,
          "capped_draws": 104,
          "coverage_status": "rated",
          "distinct_rated_opponents": 58,
          "draws": 104,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "google/gemini-3.5-flash-lite",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 46,
          "model": "google/gemini-3.5-flash-lite",
          "point_rating_method": "sequential_elo",
          "public_id": "E-9b50de854a87d3c6",
          "rated_matches": 156,
          "raw_elo_rating": 1338.4133394571838,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 26.768664341028472,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 6
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 171,
          "capped_draws": 119,
          "coverage_status": "rated",
          "distinct_rated_opponents": 63,
          "draws": 119,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "minimal",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "google/gemini-3.5-flash-lite",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 45,
          "model": "google/gemini-3.5-flash-lite",
          "point_rating_method": "sequential_elo",
          "public_id": "E-af119b49b8f1d63d",
          "rated_matches": 171,
          "raw_elo_rating": 1345.626045326663,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "minimal",
          "repair_status": "first_pass",
          "score": 27.641837520102282,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 7
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 158,
          "capped_draws": 24,
          "coverage_status": "rated",
          "distinct_rated_opponents": 62,
          "draws": 24,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "google/gemini-3.6-flash",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 26,
          "model": "google/gemini-3.6-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-620b5ca2bcd82419",
          "rated_matches": 158,
          "raw_elo_rating": 1771.3527786328943,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "first_pass",
          "score": 70.56052575945287,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 108
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 172,
          "capped_draws": 117,
          "coverage_status": "rated",
          "distinct_rated_opponents": 64,
          "draws": 117,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "minimal",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "google/gemini-3.6-flash",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 48,
          "model": "google/gemini-3.6-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-657c523bc9e9f80c",
          "rated_matches": 172,
          "raw_elo_rating": 1368.6850407942609,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "minimal",
          "repair_status": "repaired",
          "score": 29.982097403067577,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 7
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 148,
          "capped_draws": 22,
          "coverage_status": "rated",
          "distinct_rated_opponents": 62,
          "draws": 22,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "google/gemini-3.6-flash",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 35,
          "model": "google/gemini-3.6-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-ab7ee826f8050f04",
          "rated_matches": 148,
          "raw_elo_rating": 1758.2226139935103,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 69.12714958998048,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 91
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 174,
          "capped_draws": 121,
          "coverage_status": "rated",
          "distinct_rated_opponents": 65,
          "draws": 121,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "minimal",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "google/gemini-3.6-flash",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 44,
          "model": "google/gemini-3.6-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-c694a36a5e4e3f09",
          "rated_matches": 174,
          "raw_elo_rating": 1358.3892756425812,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "minimal",
          "repair_status": "first_pass",
          "score": 28.958784276838966,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 9
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 156,
          "capped_draws": 83,
          "coverage_status": "rated",
          "distinct_rated_opponents": 62,
          "draws": 83,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "google/gemini-3.6-flash",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 64,
          "model": "google/gemini-3.6-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-efad9f3f4e9183a0",
          "rated_matches": 156,
          "raw_elo_rating": 1352.379641990491,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "first_pass",
          "score": 28.18070013372008,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 9
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 118,
          "capped_draws": 94,
          "coverage_status": "rated",
          "distinct_rated_opponents": 57,
          "draws": 94,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "google/gemma-4-31b-it",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 21,
          "model": "google/gemma-4-31b-it",
          "point_rating_method": "sequential_elo",
          "public_id": "E-8546650b7690a81a",
          "rated_matches": 118,
          "raw_elo_rating": 1415.9221194161503,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 34.12535861356842,
          "uncertainty": 2.084924851410568,
          "unilateral_faults": 0,
          "wins": 3
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 108,
          "capped_draws": 79,
          "coverage_status": "rated",
          "distinct_rated_opponents": 51,
          "draws": 79,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-4.1",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "omitted",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 16,
          "model": "gpt-4.1",
          "point_rating_method": "sequential_elo",
          "public_id": "E-eabc996d553eebe0",
          "rated_matches": 108,
          "raw_elo_rating": 1418.4565971654238,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "omitted",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 34.21527625173018,
          "uncertainty": 4.1413142610575715,
          "unilateral_faults": 0,
          "wins": 13
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 90,
          "capped_draws": 56,
          "coverage_status": "rated",
          "distinct_rated_opponents": 43,
          "draws": 56,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 26,
          "model": "gpt-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-04ae9f2b42e0e036",
          "rated_matches": 90,
          "raw_elo_rating": 1347.8497544240654,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 26.71088363179663,
          "uncertainty": 8.664241836095918,
          "unilateral_faults": 0,
          "wins": 8
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 0,
          "capped_draws": 0,
          "coverage_status": "pending",
          "distinct_rated_opponents": 0,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "low",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5",
            "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-21T14:20:15Z",
          "losses": 0,
          "model": "gpt-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-ae3a897b3420bcfb",
          "rated_matches": 0,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "low",
          "repair_status": "first_pass",
          "unilateral_faults": 0,
          "wins": 0
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 114,
          "capped_draws": 66,
          "coverage_status": "rated",
          "distinct_rated_opponents": 57,
          "draws": 66,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 32,
          "model": "gpt-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-ebca8ea756b4a4ad",
          "rated_matches": 114,
          "raw_elo_rating": 1417.3165817886681,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "first_pass",
          "score": 34.20242036213885,
          "uncertainty": 2.875240412015687,
          "unilateral_faults": 0,
          "wins": 16
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 95,
          "capped_draws": 55,
          "coverage_status": "rated",
          "distinct_rated_opponents": 42,
          "draws": 55,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.4",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 35,
          "model": "gpt-5.4",
          "point_rating_method": "sequential_elo",
          "public_id": "E-07ad6c481bf678a2",
          "rated_matches": 95,
          "raw_elo_rating": 1369.4284056978859,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "repaired",
          "score": 29.00442814379102,
          "uncertainty": 7.281036307982882,
          "unilateral_faults": 0,
          "wins": 5
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 86,
          "capped_draws": 11,
          "coverage_status": "rated",
          "distinct_rated_opponents": 42,
          "draws": 11,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "xhigh",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.4",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 23,
          "model": "gpt-5.4",
          "point_rating_method": "sequential_elo",
          "public_id": "E-431ff31b9cd599e1",
          "rated_matches": 86,
          "raw_elo_rating": 1650.2502481709378,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "xhigh",
          "repair_status": "first_pass",
          "score": 57.188133954793884,
          "uncertainty": 9.855626741889738,
          "unilateral_faults": 0,
          "wins": 52
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 103,
          "capped_draws": 53,
          "coverage_status": "rated",
          "distinct_rated_opponents": 47,
          "draws": 53,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.4",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 23,
          "model": "gpt-5.4",
          "point_rating_method": "sequential_elo",
          "public_id": "E-6b601c15cf117b79",
          "rated_matches": 103,
          "raw_elo_rating": 1478.262264289942,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 40.16979011364343,
          "uncertainty": 5.279033784546012,
          "unilateral_faults": 0,
          "wins": 27
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 106,
          "capped_draws": 74,
          "coverage_status": "rated",
          "distinct_rated_opponents": 52,
          "draws": 74,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.4",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 20,
          "model": "gpt-5.4",
          "point_rating_method": "sequential_elo",
          "public_id": "E-95f891d54f35bb4a",
          "rated_matches": 106,
          "raw_elo_rating": 1440.7096875631094,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "repaired",
          "score": 36.429097626212254,
          "uncertainty": 4.586824452283178,
          "unilateral_faults": 0,
          "wins": 12
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 102,
          "capped_draws": 39,
          "coverage_status": "rated",
          "distinct_rated_opponents": 50,
          "draws": 39,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.4",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 31,
          "model": "gpt-5.4",
          "point_rating_method": "sequential_elo",
          "public_id": "E-b13a2be40d59c1ea",
          "rated_matches": 102,
          "raw_elo_rating": 1477.125133604714,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 40.03561880449786,
          "uncertainty": 5.516463908214657,
          "unilateral_faults": 0,
          "wins": 32
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 102,
          "capped_draws": 26,
          "coverage_status": "rated",
          "distinct_rated_opponents": 48,
          "draws": 26,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "xhigh",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.4",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 31,
          "model": "gpt-5.4",
          "point_rating_method": "sequential_elo",
          "public_id": "E-ddc1f3e68bf1e74a",
          "rated_matches": 102,
          "raw_elo_rating": 1614.3353490460158,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "xhigh",
          "repair_status": "first_pass",
          "score": 53.907990168643416,
          "uncertainty": 5.516463908214657,
          "unilateral_faults": 0,
          "wins": 45
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 114,
          "capped_draws": 41,
          "coverage_status": "rated",
          "distinct_rated_opponents": 54,
          "draws": 41,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.4-mini",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 38,
          "model": "gpt-5.4-mini",
          "point_rating_method": "sequential_elo",
          "public_id": "E-b5171a15f0048555",
          "rated_matches": 114,
          "raw_elo_rating": 1435.5819424274005,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 36.04910404429471,
          "uncertainty": 2.875240412015687,
          "unilateral_faults": 0,
          "wins": 35
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 92,
          "capped_draws": 77,
          "coverage_status": "rated",
          "distinct_rated_opponents": 45,
          "draws": 77,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.4-mini",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 13,
          "model": "gpt-5.4-mini",
          "point_rating_method": "sequential_elo",
          "public_id": "E-bb8ac98c284a38ce",
          "rated_matches": 90,
          "raw_elo_rating": 1400.3144399361822,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 32.01522338949161,
          "uncertainty": 8.664241836095918,
          "unilateral_faults": 2,
          "wins": 0
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 108,
          "capped_draws": 91,
          "coverage_status": "rated",
          "distinct_rated_opponents": 53,
          "draws": 91,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.4-nano",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-09T17:30:50Z",
          "losses": 17,
          "model": "gpt-5.4-nano",
          "point_rating_method": "sequential_elo",
          "public_id": "E-024aff0a983df40d",
          "rated_matches": 108,
          "raw_elo_rating": 1373.7536627261209,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 29.695673206034552,
          "uncertainty": 4.1413142610575715,
          "unilateral_faults": 0,
          "wins": 0
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 94,
          "capped_draws": 52,
          "coverage_status": "rated",
          "distinct_rated_opponents": 46,
          "draws": 52,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.4-nano",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 37,
          "model": "gpt-5.4-nano",
          "point_rating_method": "sequential_elo",
          "public_id": "E-26fa12e871bd8f3a",
          "rated_matches": 94,
          "raw_elo_rating": 1333.8577876317347,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "repaired",
          "score": 25.3864632500842,
          "uncertainty": 7.54891760425771,
          "unilateral_faults": 0,
          "wins": 5
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 94,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 46,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.4-nano",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-09T17:30:50Z",
          "losses": 22,
          "model": "gpt-5.4-nano",
          "point_rating_method": "sequential_elo",
          "public_id": "E-e361d8cbba2abd67",
          "rated_matches": 94,
          "raw_elo_rating": 1848.361904518589,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "repaired",
          "score": 77.40439904940192,
          "uncertainty": 7.54891760425771,
          "unilateral_faults": 0,
          "wins": 72
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 88,
          "capped_draws": 4,
          "coverage_status": "rated",
          "distinct_rated_opponents": 44,
          "draws": 4,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.4-nano",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 28,
          "model": "gpt-5.4-nano",
          "point_rating_method": "sequential_elo",
          "public_id": "E-fd5a36e5fd795426",
          "rated_matches": 88,
          "raw_elo_rating": 1679.920472976143,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "repaired",
          "score": 60.236877339102975,
          "uncertainty": 9.249894000318006,
          "unilateral_faults": 0,
          "wins": 56
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 112,
          "capped_draws": 50,
          "coverage_status": "rated",
          "distinct_rated_opponents": 55,
          "draws": 50,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 24,
          "model": "gpt-5.5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-0d83a3c5c5e66085",
          "rated_matches": 112,
          "raw_elo_rating": 1602.1188603960716,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 52.85326775023768,
          "uncertainty": 3.286043419179858,
          "unilateral_faults": 0,
          "wins": 38
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 104,
          "capped_draws": 16,
          "coverage_status": "rated",
          "distinct_rated_opponents": 47,
          "draws": 16,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "xhigh",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 24,
          "model": "gpt-5.5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-3e859a6b27767128",
          "rated_matches": 104,
          "raw_elo_rating": 1793.2236111969223,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "xhigh",
          "repair_status": "first_pass",
          "score": 72.03227205758726,
          "uncertainty": 5.045003647426665,
          "unilateral_faults": 0,
          "wins": 64
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 106,
          "capped_draws": 83,
          "coverage_status": "rated",
          "distinct_rated_opponents": 51,
          "draws": 83,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 19,
          "model": "gpt-5.5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-c42fbee03a029c83",
          "rated_matches": 106,
          "raw_elo_rating": 1420.0693276623153,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 34.342294273323965,
          "uncertainty": 4.586824452283178,
          "unilateral_faults": 0,
          "wins": 4
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 94,
          "capped_draws": 7,
          "coverage_status": "rated",
          "distinct_rated_opponents": 46,
          "draws": 7,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "xhigh",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.6-luna",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-10T05:30:29Z",
          "losses": 31,
          "model": "gpt-5.6-luna",
          "point_rating_method": "sequential_elo",
          "public_id": "E-0fb7de4e8156a229",
          "rated_matches": 94,
          "raw_elo_rating": 1659.815042678165,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "xhigh",
          "repair_status": "first_pass",
          "score": 58.34173612315974,
          "uncertainty": 7.54891760425771,
          "unilateral_faults": 0,
          "wins": 56
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 90,
          "capped_draws": 55,
          "coverage_status": "rated",
          "distinct_rated_opponents": 42,
          "draws": 55,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.6-luna",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 32,
          "model": "gpt-5.6-luna",
          "point_rating_method": "sequential_elo",
          "public_id": "E-283f17e4d25ffd65",
          "rated_matches": 90,
          "raw_elo_rating": 1323.5572279214625,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 24.254835093911925,
          "uncertainty": 8.664241836095918,
          "unilateral_faults": 0,
          "wins": 3
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 108,
          "capped_draws": 89,
          "coverage_status": "rated",
          "distinct_rated_opponents": 53,
          "draws": 89,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.6-luna",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-10T05:30:29Z",
          "losses": 18,
          "model": "gpt-5.6-luna",
          "point_rating_method": "sequential_elo",
          "public_id": "E-8feb37d0677409f2",
          "rated_matches": 108,
          "raw_elo_rating": 1403.3240921912495,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 32.68533383456862,
          "uncertainty": 4.1413142610575715,
          "unilateral_faults": 0,
          "wins": 1
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 90,
          "capped_draws": 12,
          "coverage_status": "rated",
          "distinct_rated_opponents": 43,
          "draws": 12,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.6-luna",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 74,
          "model": "gpt-5.6-luna",
          "point_rating_method": "sequential_elo",
          "public_id": "E-b761803f2b99649c",
          "rated_matches": 90,
          "raw_elo_rating": 1083.655118803301,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 0.0,
          "uncertainty": 8.664241836095918,
          "unilateral_faults": 0,
          "wins": 4
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 88,
          "capped_draws": 51,
          "coverage_status": "rated",
          "distinct_rated_opponents": 42,
          "draws": 51,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "xhigh",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.6-luna",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 35,
          "model": "gpt-5.6-luna",
          "point_rating_method": "sequential_elo",
          "public_id": "E-ca2978e1aca13fec",
          "rated_matches": 88,
          "raw_elo_rating": 1316.0178733440812,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "xhigh",
          "repair_status": "first_pass",
          "score": 23.445214369711753,
          "uncertainty": 9.249894000318006,
          "unilateral_faults": 0,
          "wins": 2
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 114,
          "capped_draws": 89,
          "coverage_status": "rated",
          "distinct_rated_opponents": 56,
          "draws": 89,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.6-luna",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-10T05:30:29Z",
          "losses": 18,
          "model": "gpt-5.6-luna",
          "point_rating_method": "sequential_elo",
          "public_id": "E-e6198d88365e0492",
          "rated_matches": 114,
          "raw_elo_rating": 1411.463867477643,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 33.610693090596705,
          "uncertainty": 2.875240412015687,
          "unilateral_faults": 0,
          "wins": 7
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 88,
          "capped_draws": 5,
          "coverage_status": "rated",
          "distinct_rated_opponents": 44,
          "draws": 5,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.6-sol",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-10T05:30:29Z",
          "losses": 19,
          "model": "gpt-5.6-sol",
          "point_rating_method": "sequential_elo",
          "public_id": "E-0385f0602a8e29e2",
          "rated_matches": 88,
          "raw_elo_rating": 1776.669530520418,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 70.01850220623565,
          "uncertainty": 9.249894000318006,
          "unilateral_faults": 0,
          "wins": 64
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 88,
          "capped_draws": 13,
          "coverage_status": "rated",
          "distinct_rated_opponents": 43,
          "draws": 13,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "xhigh",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.6-sol",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-10T05:30:29Z",
          "losses": 52,
          "model": "gpt-5.6-sol",
          "point_rating_method": "sequential_elo",
          "public_id": "E-3ae62f195160add3",
          "rated_matches": 88,
          "raw_elo_rating": 1356.219884706978,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "xhigh",
          "repair_status": "first_pass",
          "score": 27.509760361553635,
          "uncertainty": 9.249894000318006,
          "unilateral_faults": 0,
          "wins": 23
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 90,
          "capped_draws": 20,
          "coverage_status": "rated",
          "distinct_rated_opponents": 42,
          "draws": 20,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.6-sol",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 17,
          "model": "gpt-5.6-sol",
          "point_rating_method": "sequential_elo",
          "public_id": "E-55079a10c13f4211",
          "rated_matches": 90,
          "raw_elo_rating": 1652.9687749937566,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 57.5593474287059,
          "uncertainty": 8.664241836095918,
          "unilateral_faults": 0,
          "wins": 53
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 92,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 42,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "xhigh",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.6-sol",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 17,
          "model": "gpt-5.6-sol",
          "point_rating_method": "sequential_elo",
          "public_id": "E-58adff67f80afed1",
          "rated_matches": 92,
          "raw_elo_rating": 1859.6856893973443,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "xhigh",
          "repair_status": "first_pass",
          "score": 78.50489070907093,
          "uncertainty": 8.09758473652126,
          "unilateral_faults": 0,
          "wins": 75
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 92,
          "capped_draws": 15,
          "coverage_status": "rated",
          "distinct_rated_opponents": 46,
          "draws": 15,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.6-sol",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-10T05:30:29Z",
          "losses": 34,
          "model": "gpt-5.6-sol",
          "point_rating_method": "sequential_elo",
          "public_id": "E-994624d0bc2e266d",
          "rated_matches": 92,
          "raw_elo_rating": 1532.272527260815,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 45.402421187694905,
          "uncertainty": 8.09758473652126,
          "unilateral_faults": 0,
          "wins": 43
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 92,
          "capped_draws": 10,
          "coverage_status": "rated",
          "distinct_rated_opponents": 42,
          "draws": 10,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.6-sol",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 13,
          "model": "gpt-5.6-sol",
          "point_rating_method": "sequential_elo",
          "public_id": "E-9c0688f3432e6295",
          "rated_matches": 92,
          "raw_elo_rating": 1802.6772398837727,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 72.74116254930627,
          "uncertainty": 8.09758473652126,
          "unilateral_faults": 0,
          "wins": 69
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 102,
          "capped_draws": 74,
          "coverage_status": "rated",
          "distinct_rated_opponents": 50,
          "draws": 74,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.6-terra",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-10T05:30:29Z",
          "losses": 23,
          "model": "gpt-5.6-terra",
          "point_rating_method": "sequential_elo",
          "public_id": "E-44cace55a6126cdf",
          "rated_matches": 100,
          "raw_elo_rating": 1391.0357740645313,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 31.292461943857255,
          "uncertainty": 6.001859510499461,
          "unilateral_faults": 2,
          "wins": 3
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 100,
          "capped_draws": 15,
          "coverage_status": "rated",
          "distinct_rated_opponents": 47,
          "draws": 15,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "xhigh",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.6-terra",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-10T05:30:29Z",
          "losses": 33,
          "model": "gpt-5.6-terra",
          "point_rating_method": "sequential_elo",
          "public_id": "E-b061663dc342c859",
          "rated_matches": 100,
          "raw_elo_rating": 1623.2810218217542,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "xhigh",
          "repair_status": "repaired",
          "score": 54.77316499562428,
          "uncertainty": 6.001859510499461,
          "unilateral_faults": 0,
          "wins": 52
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 108,
          "capped_draws": 53,
          "coverage_status": "rated",
          "distinct_rated_opponents": 53,
          "draws": 53,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.6-terra",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-10T05:30:29Z",
          "losses": 34,
          "model": "gpt-5.6-terra",
          "point_rating_method": "sequential_elo",
          "public_id": "E-d004e78844cdd202",
          "rated_matches": 108,
          "raw_elo_rating": 1480.0543554717117,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 40.442997530903185,
          "uncertainty": 4.1413142610575715,
          "unilateral_faults": 0,
          "wins": 21
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 160,
          "capped_draws": 140,
          "coverage_status": "rated",
          "distinct_rated_opponents": 57,
          "draws": 140,
          "evaluated_setting_identity": {
            "canonical_provider_route": "unknown_legacy",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "inclusionai/ling-3.0-flash:free",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 16,
          "model": "inclusionai/ling-3.0-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-11d1ae7d9526f835",
          "rated_matches": 156,
          "raw_elo_rating": 1377.9725394945106,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 30.768220146850258,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 0
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 158,
          "capped_draws": 132,
          "coverage_status": "rated",
          "distinct_rated_opponents": 61,
          "draws": 132,
          "evaluated_setting_identity": {
            "canonical_provider_route": "unknown_legacy",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "inclusionai/ling-3.0-flash:free",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 21,
          "model": "inclusionai/ling-3.0-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-28bcc8394e411616",
          "rated_matches": 158,
          "raw_elo_rating": 1365.25374003325,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "none",
          "repair_status": "repaired",
          "score": 29.50267408304644,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 5
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 114,
          "capped_draws": 103,
          "coverage_status": "rated",
          "distinct_rated_opponents": 54,
          "draws": 103,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "meituan/longcat-2.0",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 10,
          "model": "meituan/longcat-2.0",
          "point_rating_method": "sequential_elo",
          "public_id": "E-87d69837bf65e78b",
          "rated_matches": 114,
          "raw_elo_rating": 1374.243883454029,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 29.847639159936406,
          "uncertainty": 2.875240412015687,
          "unilateral_faults": 0,
          "wins": 1
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 168,
          "capped_draws": 47,
          "coverage_status": "rated",
          "distinct_rated_opponents": 61,
          "draws": 47,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "enabled",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "meituan/longcat-2.0",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 120,
          "model": "meituan/longcat-2.0",
          "point_rating_method": "sequential_elo",
          "public_id": "E-d724da56cbc06da7",
          "rated_matches": 168,
          "raw_elo_rating": 1121.9065676781295,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "enabled",
          "repair_status": "first_pass",
          "score": 4.995866874780885,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 1
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 116,
          "capped_draws": 97,
          "coverage_status": "rated",
          "distinct_rated_opponents": 55,
          "draws": 97,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "meituan/longcat-2.0",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 12,
          "model": "meituan/longcat-2.0",
          "point_rating_method": "sequential_elo",
          "public_id": "E-df8e0fab4bf8bb33",
          "rated_matches": 116,
          "raw_elo_rating": 1399.6109186599392,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 32.44469490442338,
          "uncertainty": 2.4750163521024238,
          "unilateral_faults": 0,
          "wins": 7
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 143,
          "capped_draws": 50,
          "coverage_status": "rated",
          "distinct_rated_opponents": 59,
          "draws": 50,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "enabled",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "meituan/longcat-2.0",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 34,
          "model": "meituan/longcat-2.0",
          "point_rating_method": "sequential_elo",
          "public_id": "E-ef389910f6cc07cc",
          "rated_matches": 143,
          "raw_elo_rating": 1617.7535583908511,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "enabled",
          "repair_status": "first_pass",
          "score": 54.86827170970613,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 59
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 90,
          "capped_draws": 4,
          "coverage_status": "rated",
          "distinct_rated_opponents": 42,
          "draws": 4,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "minimal",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "meta/muse-spark-1.2",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-08-13T16:58:34Z",
          "losses": 33,
          "model": "meta/muse-spark-1.2",
          "point_rating_method": "sequential_elo",
          "public_id": "E-20b4e41aba8e4f47",
          "rated_matches": 90,
          "raw_elo_rating": 1653.2616124943645,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "minimal",
          "repair_status": "first_pass",
          "score": 57.58895419336781,
          "uncertainty": 8.664241836095918,
          "unilateral_faults": 0,
          "wins": 53
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 90,
          "capped_draws": 16,
          "coverage_status": "rated",
          "distinct_rated_opponents": 42,
          "draws": 16,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "meta/muse-spark-1.2",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-08-13T16:58:34Z",
          "losses": 19,
          "model": "meta/muse-spark-1.2",
          "point_rating_method": "sequential_elo",
          "public_id": "E-502a038b3a2d63ef",
          "rated_matches": 90,
          "raw_elo_rating": 1697.4882744755037,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 62.06040464059319,
          "uncertainty": 8.664241836095918,
          "unilateral_faults": 0,
          "wins": 55
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 116,
          "capped_draws": 90,
          "coverage_status": "rated",
          "distinct_rated_opponents": 53,
          "draws": 90,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "enabled",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "minimax/minimax-m3",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 19,
          "model": "minimax/minimax-m3",
          "point_rating_method": "sequential_elo",
          "public_id": "E-d169e7b29be70652",
          "rated_matches": 116,
          "raw_elo_rating": 1411.9719926684977,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "enabled",
          "repair_status": "repaired",
          "score": 33.69443719624106,
          "uncertainty": 2.4750163521024238,
          "unilateral_faults": 0,
          "wins": 7
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 96,
          "capped_draws": 7,
          "coverage_status": "rated",
          "distinct_rated_opponents": 48,
          "draws": 7,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "minimax/minimax-m3",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 49,
          "model": "minimax/minimax-m3",
          "point_rating_method": "sequential_elo",
          "public_id": "E-e67e41d4491d7ad3",
          "rated_matches": 96,
          "raw_elo_rating": 1508.5181338037046,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 43.08815494051834,
          "uncertainty": 7.017308256680951,
          "unilateral_faults": 0,
          "wins": 40
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 116,
          "capped_draws": 92,
          "coverage_status": "rated",
          "distinct_rated_opponents": 58,
          "draws": 92,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "mistralai/mistral-medium-3-5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 22,
          "model": "mistralai/mistral-medium-3-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-ba85be2fa53925f5",
          "rated_matches": 116,
          "raw_elo_rating": 1354.8843322134849,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 27.922700568650274,
          "uncertainty": 2.4750163521024238,
          "unilateral_faults": 0,
          "wins": 2
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 98,
          "capped_draws": 10,
          "coverage_status": "rated",
          "distinct_rated_opponents": 45,
          "draws": 10,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "enabled",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "moonshotai/kimi-k2.7-code",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 30,
          "model": "moonshotai/kimi-k2.7-code",
          "point_rating_method": "sequential_elo",
          "public_id": "E-251b5d53a5f89562",
          "rated_matches": 98,
          "raw_elo_rating": 1716.3352365750259,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "enabled",
          "repair_status": "repaired",
          "score": 64.14078623679886,
          "uncertainty": 6.501890762960602,
          "unilateral_faults": 0,
          "wins": 58
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 192,
          "capped_draws": 134,
          "coverage_status": "rated",
          "distinct_rated_opponents": 75,
          "draws": 134,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "moonshotai/kimi-k3",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T14:00:00Z",
          "losses": 46,
          "model": "moonshotai/kimi-k3",
          "point_rating_method": "sequential_elo",
          "public_id": "E-151c4ee6a2d1838e",
          "rated_matches": 192,
          "raw_elo_rating": 1378.0442055713736,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "first_pass",
          "score": 31.092003821784623,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 12
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 178,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 70,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "low",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "moonshotai/kimi-k3",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T14:00:00Z",
          "losses": 8,
          "model": "moonshotai/kimi-k3",
          "point_rating_method": "sequential_elo",
          "public_id": "E-3e1be56b9d966ded",
          "rated_matches": 178,
          "raw_elo_rating": 2021.4459228627536,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "low",
          "repair_status": "first_pass",
          "score": 96.03018425662745,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 170
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 110,
          "capped_draws": 96,
          "coverage_status": "rated",
          "distinct_rated_opponents": 54,
          "draws": 96,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "nex-agi/nex-n2-pro",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-11T17:22:09Z",
          "losses": 14,
          "model": "nex-agi/nex-n2-pro",
          "point_rating_method": "sequential_elo",
          "public_id": "E-506d972b5c69a00d",
          "rated_matches": 110,
          "raw_elo_rating": 1403.0243582764076,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "none",
          "repair_status": "repaired",
          "score": 32.69008544176368,
          "uncertainty": 3.707899787624953,
          "unilateral_faults": 0,
          "wins": 0
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 92,
          "capped_draws": 13,
          "coverage_status": "rated",
          "distinct_rated_opponents": 44,
          "draws": 13,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "enabled",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "nex-agi/nex-n2-pro",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 71,
          "model": "nex-agi/nex-n2-pro",
          "point_rating_method": "sequential_elo",
          "public_id": "E-92332f4d765b2297",
          "rated_matches": 92,
          "raw_elo_rating": 1194.9426957801345,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "enabled",
          "repair_status": "repaired",
          "score": 11.297346143143717,
          "uncertainty": 8.09758473652126,
          "unilateral_faults": 0,
          "wins": 8
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 110,
          "capped_draws": 74,
          "coverage_status": "rated",
          "distinct_rated_opponents": 55,
          "draws": 74,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "nvidia/nemotron-3-ultra-550b-a55b",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 27,
          "model": "nvidia/nemotron-3-ultra-550b-a55b",
          "point_rating_method": "sequential_elo",
          "public_id": "E-15cf0dede27b7e1b",
          "rated_matches": 110,
          "raw_elo_rating": 1406.0071008564112,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "repaired",
          "score": 32.99164981596408,
          "uncertainty": 3.707899787624953,
          "unilateral_faults": 0,
          "wins": 9
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 104,
          "capped_draws": 68,
          "coverage_status": "rated",
          "distinct_rated_opponents": 51,
          "draws": 68,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "nvidia/nemotron-3-ultra-550b-a55b",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-11T17:22:09Z",
          "losses": 26,
          "model": "nvidia/nemotron-3-ultra-550b-a55b",
          "point_rating_method": "sequential_elo",
          "public_id": "E-2e3c01d0103fc439",
          "rated_matches": 104,
          "raw_elo_rating": 1398.2805327368721,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "repaired",
          "score": 32.102321984441986,
          "uncertainty": 5.045003647426665,
          "unilateral_faults": 0,
          "wins": 10
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 92,
          "capped_draws": 64,
          "coverage_status": "rated",
          "distinct_rated_opponents": 44,
          "draws": 64,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "nvidia/nemotron-3-ultra-550b-a55b",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 23,
          "model": "nvidia/nemotron-3-ultra-550b-a55b",
          "point_rating_method": "sequential_elo",
          "public_id": "E-8c24e8bcbe9b1228",
          "rated_matches": 92,
          "raw_elo_rating": 1397.4647466210838,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "first_pass",
          "score": 31.77294331102291,
          "uncertainty": 8.09758473652126,
          "unilateral_faults": 0,
          "wins": 5
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 84,
          "capped_draws": 78,
          "coverage_status": "rated",
          "distinct_rated_opponents": 42,
          "draws": 78,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "nvidia/nemotron-3-ultra-550b-a55b",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 5,
          "model": "nvidia/nemotron-3-ultra-550b-a55b",
          "point_rating_method": "sequential_elo",
          "public_id": "E-ada32b27ea6ffedd",
          "rated_matches": 84,
          "raw_elo_rating": 1422.0047853601131,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 34.06110906673491,
          "uncertainty": 10.482614454664043,
          "unilateral_faults": 0,
          "wins": 1
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 158,
          "capped_draws": 1,
          "coverage_status": "rated",
          "distinct_rated_opponents": 62,
          "draws": 1,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "o3",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-03T16:00:00Z",
          "losses": 35,
          "model": "o3",
          "point_rating_method": "sequential_elo",
          "public_id": "E-2270b9df7d2b32cc",
          "rated_matches": 158,
          "raw_elo_rating": 1799.6635648752338,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "first_pass",
          "score": 73.42283261540769,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 122
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 163,
          "capped_draws": 111,
          "coverage_status": "rated",
          "distinct_rated_opponents": 64,
          "draws": 111,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "low",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "o3",
            "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-21T14:20:15Z",
          "losses": 47,
          "model": "o3",
          "point_rating_method": "sequential_elo",
          "public_id": "E-335ae90fdc702bd6",
          "rated_matches": 163,
          "raw_elo_rating": 1346.4376685189152,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "low",
          "repair_status": "first_pass",
          "score": 27.649580485211807,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 5
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 124,
          "capped_draws": 63,
          "coverage_status": "rated",
          "distinct_rated_opponents": 61,
          "draws": 63,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "o3",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 32,
          "model": "o3",
          "point_rating_method": "sequential_elo",
          "public_id": "E-35de956c8305ff90",
          "rated_matches": 124,
          "raw_elo_rating": 1463.6955904890767,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 39.04547015939034,
          "uncertainty": 0.9713595499957961,
          "unilateral_faults": 0,
          "wins": 29
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 152,
          "capped_draws": 84,
          "coverage_status": "rated",
          "distinct_rated_opponents": 62,
          "draws": 84,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "o3",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-03T15:45:00Z",
          "losses": 60,
          "model": "o3",
          "point_rating_method": "sequential_elo",
          "public_id": "E-9fbb8e6c69f575f4",
          "rated_matches": 152,
          "raw_elo_rating": 1318.8921498651468,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "first_pass",
          "score": 24.753094391039728,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 8
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 168,
          "capped_draws": 106,
          "coverage_status": "rated",
          "distinct_rated_opponents": 64,
          "draws": 106,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "o3",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 50,
          "model": "o3",
          "point_rating_method": "sequential_elo",
          "public_id": "E-afa6c09eebc859c4",
          "rated_matches": 168,
          "raw_elo_rating": 1410.309112947049,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "first_pass",
          "score": 34.154244022339505,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 12
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 94,
          "capped_draws": 67,
          "coverage_status": "rated",
          "distinct_rated_opponents": 45,
          "draws": 67,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "openai/gpt-oss-120b",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 22,
          "model": "openai/gpt-oss-120b",
          "point_rating_method": "sequential_elo",
          "public_id": "E-24a75273941e6ea3",
          "rated_matches": 94,
          "raw_elo_rating": 1400.2862698488254,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "repaired",
          "score": 32.10258545358184,
          "uncertainty": 7.54891760425771,
          "unilateral_faults": 0,
          "wins": 5
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 118,
          "capped_draws": 86,
          "coverage_status": "rated",
          "distinct_rated_opponents": 56,
          "draws": 86,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "openai/gpt-oss-120b",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 23,
          "model": "openai/gpt-oss-120b",
          "point_rating_method": "sequential_elo",
          "public_id": "E-6e65dec497ff2de3",
          "rated_matches": 118,
          "raw_elo_rating": 1421.642551452285,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "repaired",
          "score": 34.70371174356963,
          "uncertainty": 2.084924851410568,
          "unilateral_faults": 0,
          "wins": 9
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 158,
          "capped_draws": 94,
          "coverage_status": "rated",
          "distinct_rated_opponents": 66,
          "draws": 94,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "low",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "openai/gpt-oss-120b",
            "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-21T14:20:15Z",
          "losses": 60,
          "model": "openai/gpt-oss-120b",
          "point_rating_method": "sequential_elo",
          "public_id": "E-f6e9da46c61ad315",
          "rated_matches": 158,
          "raw_elo_rating": 1270.3817645663387,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "low",
          "repair_status": "first_pass",
          "score": 19.910827940292407,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 4
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 172,
          "capped_draws": 117,
          "coverage_status": "rated",
          "distinct_rated_opponents": 66,
          "draws": 117,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "enabled",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "poolside/laguna-s-2.1",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 48,
          "model": "poolside/laguna-s-2.1",
          "point_rating_method": "sequential_elo",
          "public_id": "E-0fab95afbec0dd98",
          "rated_matches": 172,
          "raw_elo_rating": 1349.8114450883386,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "enabled",
          "repair_status": "first_pass",
          "score": 28.073919300094598,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 7
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 116,
          "capped_draws": 100,
          "coverage_status": "rated",
          "distinct_rated_opponents": 55,
          "draws": 100,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "poolside/laguna-s-2.1",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 13,
          "model": "poolside/laguna-s-2.1",
          "point_rating_method": "sequential_elo",
          "public_id": "E-4030acdbccf3ca03",
          "rated_matches": 116,
          "raw_elo_rating": 1380.5080334570664,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "none",
          "repair_status": "repaired",
          "score": 30.51333493382221,
          "uncertainty": 2.4750163521024238,
          "unilateral_faults": 0,
          "wins": 3
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 114,
          "capped_draws": 95,
          "coverage_status": "rated",
          "distinct_rated_opponents": 54,
          "draws": 95,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "poolside/laguna-s-2.1",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 16,
          "model": "poolside/laguna-s-2.1",
          "point_rating_method": "sequential_elo",
          "public_id": "E-e90a3ce84847ba43",
          "rated_matches": 114,
          "raw_elo_rating": 1386.4592518812346,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 31.08265017297974,
          "uncertainty": 2.875240412015687,
          "unilateral_faults": 0,
          "wins": 3
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 172,
          "capped_draws": 118,
          "coverage_status": "rated",
          "distinct_rated_opponents": 66,
          "draws": 118,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "enabled",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "poolside/laguna-s-2.1",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 47,
          "model": "poolside/laguna-s-2.1",
          "point_rating_method": "sequential_elo",
          "public_id": "E-f72c72b8f264c57a",
          "rated_matches": 172,
          "raw_elo_rating": 1358.3761132030627,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "enabled",
          "repair_status": "first_pass",
          "score": 28.93983337446566,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 7
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 118,
          "capped_draws": 76,
          "coverage_status": "rated",
          "distinct_rated_opponents": 55,
          "draws": 76,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "enabled",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "qwen/qwen3.7-max",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 31,
          "model": "qwen/qwen3.7-max",
          "point_rating_method": "sequential_elo",
          "public_id": "E-64624689e7cbd439",
          "rated_matches": 118,
          "raw_elo_rating": 1440.8004114495486,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "enabled",
          "repair_status": "repaired",
          "score": 36.640629833593636,
          "uncertainty": 2.084924851410568,
          "unilateral_faults": 0,
          "wins": 11
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 110,
          "capped_draws": 76,
          "coverage_status": "rated",
          "distinct_rated_opponents": 54,
          "draws": 76,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "qwen/qwen3.7-max",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 30,
          "model": "qwen/qwen3.7-max",
          "point_rating_method": "sequential_elo",
          "public_id": "E-a667eb7d15f7f43e",
          "rated_matches": 110,
          "raw_elo_rating": 1397.181675768906,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 32.09937241616148,
          "uncertainty": 3.707899787624953,
          "unilateral_faults": 0,
          "wins": 4
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 114,
          "capped_draws": 94,
          "coverage_status": "rated",
          "distinct_rated_opponents": 54,
          "draws": 94,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "enabled",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "qwen/qwen3.7-plus",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 20,
          "model": "qwen/qwen3.7-plus",
          "point_rating_method": "sequential_elo",
          "public_id": "E-6c2a9942e92223c8",
          "rated_matches": 114,
          "raw_elo_rating": 1415.39305533373,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "enabled",
          "repair_status": "first_pass",
          "score": 34.007945969500966,
          "uncertainty": 2.875240412015687,
          "unilateral_faults": 0,
          "wins": 0
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 18,
          "capped_draws": 5,
          "coverage_status": "under_covered",
          "distinct_rated_opponents": 7,
          "draws": 5,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "qwen/qwen3.8-max",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 2,
          "model": "qwen/qwen3.8-max",
          "point_rating_method": "sequential_elo",
          "public_id": "E-58e68aa5bf529b8a",
          "rated_matches": 18,
          "raw_elo_rating": 1632.9497775865889,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 50.496905291659246,
          "uncertainty": 70.95786693528086,
          "unilateral_faults": 0,
          "wins": 11
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 16,
          "capped_draws": 13,
          "coverage_status": "under_covered",
          "distinct_rated_opponents": 7,
          "draws": 13,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "minimal",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "qwen/qwen3.8-max",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 0,
          "model": "qwen/qwen3.8-max",
          "point_rating_method": "sequential_elo",
          "public_id": "E-e77a22943f077d4d",
          "rated_matches": 16,
          "raw_elo_rating": 1535.5507689243868,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "minimal",
          "repair_status": "first_pass",
          "score": 40.11898397519311,
          "uncertainty": 77.5178125181665,
          "unilateral_faults": 0,
          "wins": 3
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 18,
          "capped_draws": 12,
          "coverage_status": "under_covered",
          "distinct_rated_opponents": 8,
          "draws": 12,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "xhigh",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "qwen/qwen3.8-max",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-08-18T17:01:47Z",
          "losses": 4,
          "model": "qwen/qwen3.8-max",
          "point_rating_method": "sequential_elo",
          "public_id": "E-eef649e110a96b98",
          "rated_matches": 18,
          "raw_elo_rating": 1453.2655519062441,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "xhigh",
          "repair_status": "first_pass",
          "score": 32.3302819181756,
          "uncertainty": 70.95786693528086,
          "unilateral_faults": 0,
          "wins": 2
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 14,
          "capped_draws": 7,
          "coverage_status": "rated",
          "distinct_rated_opponents": 7,
          "draws": 7,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "stealth/ox-alpha",
            "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-08-22T00:27:26Z",
          "losses": 4,
          "model": "stealth/ox-alpha",
          "point_rating_method": "sequential_elo",
          "public_id": "E-273045858e4a7f82",
          "rated_matches": 14,
          "raw_elo_rating": 1484.4731032493053,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "first_pass",
          "score": 34.32143461607768,
          "uncertainty": 85.34944487358055,
          "unilateral_faults": 0,
          "wins": 3
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 14,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 7,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "max",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "stealth/ox-alpha",
            "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-08-22T00:27:26Z",
          "losses": 0,
          "model": "stealth/ox-alpha",
          "point_rating_method": "sequential_elo",
          "public_id": "E-27b1ec2d9d5762a4",
          "rated_matches": 14,
          "raw_elo_rating": 1670.7371927792685,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "max",
          "repair_status": "first_pass",
          "score": 53.153302297748226,
          "uncertainty": 85.34944487358055,
          "unilateral_faults": 0,
          "wins": 14
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 14,
          "capped_draws": 5,
          "coverage_status": "rated",
          "distinct_rated_opponents": 7,
          "draws": 5,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "low",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "stealth/ox-alpha",
            "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-08-22T00:27:26Z",
          "losses": 9,
          "model": "stealth/ox-alpha",
          "point_rating_method": "sequential_elo",
          "public_id": "E-4e4d3135cae0253d",
          "rated_matches": 14,
          "raw_elo_rating": 1392.9698450978076,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "low",
          "repair_status": "first_pass",
          "score": 25.0701760707554,
          "uncertainty": 85.34944487358055,
          "unilateral_faults": 0,
          "wins": 0
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 14,
          "capped_draws": 6,
          "coverage_status": "rated",
          "distinct_rated_opponents": 7,
          "draws": 6,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "low",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "stealth/ox-alpha",
            "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-08-22T00:27:26Z",
          "losses": 8,
          "model": "stealth/ox-alpha",
          "point_rating_method": "sequential_elo",
          "public_id": "E-6b99e270ec28f9cf",
          "rated_matches": 14,
          "raw_elo_rating": 1403.200935100437,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "low",
          "repair_status": "first_pass",
          "score": 26.104570481696243,
          "uncertainty": 85.34944487358055,
          "unilateral_faults": 0,
          "wins": 0
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 14,
          "capped_draws": 3,
          "coverage_status": "rated",
          "distinct_rated_opponents": 7,
          "draws": 3,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "stealth/ox-alpha",
            "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-08-22T00:27:26Z",
          "losses": 3,
          "model": "stealth/ox-alpha",
          "point_rating_method": "sequential_elo",
          "public_id": "E-8094ab91b5be5ad0",
          "rated_matches": 14,
          "raw_elo_rating": 1563.4373437594195,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "first_pass",
          "score": 42.30496022545644,
          "uncertainty": 85.34944487358055,
          "unilateral_faults": 0,
          "wins": 8
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 14,
          "capped_draws": 7,
          "coverage_status": "rated",
          "distinct_rated_opponents": 7,
          "draws": 7,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "stealth/ox-alpha",
            "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-08-22T00:27:26Z",
          "losses": 6,
          "model": "stealth/ox-alpha",
          "point_rating_method": "sequential_elo",
          "public_id": "E-a87ab54ca8c5ca34",
          "rated_matches": 14,
          "raw_elo_rating": 1444.3642926806658,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "repaired",
          "score": 30.26631150886005,
          "uncertainty": 85.34944487358055,
          "unilateral_faults": 0,
          "wins": 1
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 14,
          "capped_draws": 7,
          "coverage_status": "rated",
          "distinct_rated_opponents": 7,
          "draws": 7,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "max",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "stealth/ox-alpha",
            "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-08-22T00:27:26Z",
          "losses": 4,
          "model": "stealth/ox-alpha",
          "point_rating_method": "sequential_elo",
          "public_id": "E-ec8f506d56ff547e",
          "rated_matches": 14,
          "raw_elo_rating": 1481.0792078166126,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "max",
          "repair_status": "first_pass",
          "score": 33.9783014341789,
          "uncertainty": 85.34944487358055,
          "unilateral_faults": 0,
          "wins": 3
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 14,
          "capped_draws": 3,
          "coverage_status": "rated",
          "distinct_rated_opponents": 7,
          "draws": 3,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "max",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "stealth/ox-alpha",
            "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-08-22T00:27:26Z",
          "losses": 3,
          "model": "stealth/ox-alpha",
          "point_rating_method": "sequential_elo",
          "public_id": "E-f84aa60bad19339a",
          "rated_matches": 14,
          "raw_elo_rating": 1559.7380795164838,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "max",
          "repair_status": "first_pass",
          "score": 41.93095332526276,
          "uncertainty": 85.34944487358055,
          "unilateral_faults": 0,
          "wins": 8
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 92,
          "capped_draws": 70,
          "coverage_status": "rated",
          "distinct_rated_opponents": 44,
          "draws": 70,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "stepfun/step-3.7-flash",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 21,
          "model": "stepfun/step-3.7-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-8b265019ada47f24",
          "rated_matches": 92,
          "raw_elo_rating": 1385.5425180436987,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "repaired",
          "score": 30.56756963106926,
          "uncertainty": 8.09758473652126,
          "unilateral_faults": 0,
          "wins": 1
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 158,
          "capped_draws": 104,
          "coverage_status": "rated",
          "distinct_rated_opponents": 66,
          "draws": 104,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "low",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "stepfun/step-3.7-flash",
            "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-21T14:20:15Z",
          "losses": 54,
          "model": "stepfun/step-3.7-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-c38fe2712e69333b",
          "rated_matches": 158,
          "raw_elo_rating": 1292.208218512245,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "low",
          "repair_status": "first_pass",
          "score": 22.117549019522556,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 0
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 114,
          "capped_draws": 90,
          "coverage_status": "rated",
          "distinct_rated_opponents": 55,
          "draws": 90,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "tencent/hy3-preview",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 21,
          "model": "tencent/hy3-preview",
          "point_rating_method": "sequential_elo",
          "public_id": "E-56487337fad4192f",
          "rated_matches": 114,
          "raw_elo_rating": 1417.9497965630508,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 34.26644030755798,
          "uncertainty": 2.875240412015687,
          "unilateral_faults": 0,
          "wins": 3
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 104,
          "capped_draws": 26,
          "coverage_status": "rated",
          "distinct_rated_opponents": 51,
          "draws": 26,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "tencent/hy3-preview",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 45,
          "model": "tencent/hy3-preview",
          "point_rating_method": "sequential_elo",
          "public_id": "E-81a5e5ef15f371dc",
          "rated_matches": 104,
          "raw_elo_rating": 1457.8491002180717,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "first_pass",
          "score": 38.12488588080784,
          "uncertainty": 5.045003647426665,
          "unilateral_faults": 0,
          "wins": 33
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 114,
          "capped_draws": 7,
          "coverage_status": "rated",
          "distinct_rated_opponents": 55,
          "draws": 7,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "thinkingmachines/inkling",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 37,
          "model": "thinkingmachines/inkling",
          "point_rating_method": "sequential_elo",
          "public_id": "E-68669040dc891a7d",
          "rated_matches": 114,
          "raw_elo_rating": 1751.0420667004444,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "repaired",
          "score": 67.94308497290339,
          "uncertainty": 2.875240412015687,
          "unilateral_faults": 0,
          "wins": 70
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 157,
          "capped_draws": 96,
          "coverage_status": "rated",
          "distinct_rated_opponents": 60,
          "draws": 96,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "thinkingmachines/inkling",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 50,
          "model": "thinkingmachines/inkling",
          "point_rating_method": "sequential_elo",
          "public_id": "E-9f74dab09049a473",
          "rated_matches": 157,
          "raw_elo_rating": 1328.7976684792145,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 25.806720683180234,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 11
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 178,
          "capped_draws": 103,
          "coverage_status": "rated",
          "distinct_rated_opponents": 67,
          "draws": 103,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "max",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "thinkingmachines/inkling",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 71,
          "model": "thinkingmachines/inkling",
          "point_rating_method": "sequential_elo",
          "public_id": "E-d21921560d198b28",
          "rated_matches": 178,
          "raw_elo_rating": 1337.923250186877,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "max",
          "repair_status": "repaired",
          "score": 26.923956847273455,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 4
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 17,
          "capped_draws": 16,
          "coverage_status": "under_covered",
          "distinct_rated_opponents": 8,
          "draws": 16,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "max",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "thinkingmachines/inkling-small",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 1,
          "model": "thinkingmachines/inkling-small",
          "point_rating_method": "sequential_elo",
          "public_id": "E-888363fef76ee16a",
          "rated_matches": 17,
          "raw_elo_rating": 1468.4221652498795,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "max",
          "repair_status": "repaired",
          "score": 33.608426961121125,
          "uncertainty": 74.10113019775793,
          "unilateral_faults": 0,
          "wins": 0
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 14,
          "capped_draws": 10,
          "coverage_status": "under_covered",
          "distinct_rated_opponents": 6,
          "draws": 10,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "thinkingmachines/inkling-small",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 4,
          "model": "thinkingmachines/inkling-small",
          "point_rating_method": "sequential_elo",
          "public_id": "E-99211d414b6fcc51",
          "rated_matches": 14,
          "raw_elo_rating": 1452.7011179104888,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "repaired",
          "score": 31.109189972494256,
          "uncertainty": 85.34944487358055,
          "unilateral_faults": 0,
          "wins": 0
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 15,
          "capped_draws": 12,
          "coverage_status": "under_covered",
          "distinct_rated_opponents": 7,
          "draws": 12,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "thinkingmachines/inkling-small",
            "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "losses": 3,
          "model": "thinkingmachines/inkling-small",
          "point_rating_method": "sequential_elo",
          "public_id": "E-9cd2fd1302bb65bd",
          "rated_matches": 15,
          "raw_elo_rating": 1460.0832035786366,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 32.187114460064755,
          "uncertainty": 81.25,
          "unilateral_faults": 0,
          "wins": 0
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 178,
          "capped_draws": 2,
          "coverage_status": "rated",
          "distinct_rated_opponents": 68,
          "draws": 2,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "x-ai/grok-4.5",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T14:00:00Z",
          "losses": 20,
          "model": "x-ai/grok-4.5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-707dd709e358a173",
          "rated_matches": 178,
          "raw_elo_rating": 1958.1843507591848,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "first_pass",
          "score": 89.63424632680322,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 156
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 102,
          "capped_draws": 1,
          "coverage_status": "rated",
          "distinct_rated_opponents": 51,
          "draws": 1,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "x-ai/grok-4.5",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T14:00:00Z",
          "losses": 14,
          "model": "x-ai/grok-4.5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-73422318071a105c",
          "rated_matches": 102,
          "raw_elo_rating": 1930.9765683598841,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "first_pass",
          "score": 85.92138340901016,
          "uncertainty": 5.516463908214657,
          "unilateral_faults": 0,
          "wins": 87
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 174,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 72,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "low",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "x-ai/grok-4.5",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T14:00:00Z",
          "losses": 27,
          "model": "x-ai/grok-4.5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-b914d026c7631fcb",
          "rated_matches": 174,
          "raw_elo_rating": 1900.781455166142,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
          "reasoning_policy_version": "gb2_reasoning_brackets_v2",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "low",
          "repair_status": "first_pass",
          "score": 83.79628828599199,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 147
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 114,
          "capped_draws": 93,
          "coverage_status": "rated",
          "distinct_rated_opponents": 56,
          "draws": 93,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "enabled",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "x-ai/grok-build-0.1",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 15,
          "model": "x-ai/grok-build-0.1",
          "point_rating_method": "sequential_elo",
          "public_id": "E-3e2fe948d2bcebb0",
          "rated_matches": 114,
          "raw_elo_rating": 1404.4257773948275,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "enabled",
          "repair_status": "repaired",
          "score": 32.89912071233677,
          "uncertainty": 2.875240412015687,
          "unilateral_faults": 0,
          "wins": 6
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 78,
          "capped_draws": 71,
          "coverage_status": "rated",
          "distinct_rated_opponents": 39,
          "draws": 71,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "xiaomi/mimo-v2.5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T06:10:40Z",
          "losses": 5,
          "model": "xiaomi/mimo-v2.5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-5f664f9580459829",
          "rated_matches": 78,
          "raw_elo_rating": 1390.6857995210323,
          "reasoning": "highest",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "repaired",
          "score": 30.7311375060473,
          "uncertainty": 12.5043950463012,
          "unilateral_faults": 0,
          "wins": 2
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 104,
          "capped_draws": 53,
          "coverage_status": "rated",
          "distinct_rated_opponents": 50,
          "draws": 53,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "enabled",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "xiaomi/mimo-v2.5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-03T19:35:00Z",
          "losses": 30,
          "model": "xiaomi/mimo-v2.5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-650d06103e7fa176",
          "rated_matches": 104,
          "raw_elo_rating": 1485.4249105169813,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "enabled",
          "repair_status": "repaired",
          "score": 40.91288442671314,
          "uncertainty": 5.045003647426665,
          "unilateral_faults": 0,
          "wins": 21
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 94,
          "capped_draws": 45,
          "coverage_status": "rated",
          "distinct_rated_opponents": 44,
          "draws": 45,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "xiaomi/mimo-v2.5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T06:10:40Z",
          "losses": 46,
          "model": "xiaomi/mimo-v2.5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-b5eb7da0f5021b69",
          "rated_matches": 94,
          "raw_elo_rating": 1275.0559963930348,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "repaired",
          "score": 19.44142277101602,
          "uncertainty": 7.54891760425771,
          "unilateral_faults": 0,
          "wins": 3
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 96,
          "capped_draws": 60,
          "coverage_status": "rated",
          "distinct_rated_opponents": 48,
          "draws": 60,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "xiaomi/mimo-v2.5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 34,
          "model": "xiaomi/mimo-v2.5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-cabbf604f15eb575",
          "rated_matches": 96,
          "raw_elo_rating": 1302.9215821989426,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 22.301716366131743,
          "uncertainty": 7.017308256680951,
          "unilateral_faults": 0,
          "wins": 2
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 92,
          "capped_draws": 74,
          "coverage_status": "rated",
          "distinct_rated_opponents": 46,
          "draws": 74,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "xiaomi/mimo-v2.5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-01T00:15:48Z",
          "losses": 16,
          "model": "xiaomi/mimo-v2.5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-d51fce0298267f96",
          "rated_matches": 92,
          "raw_elo_rating": 1393.1451787133317,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 31.33622181797477,
          "uncertainty": 8.09758473652126,
          "unilateral_faults": 0,
          "wins": 2
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 102,
          "capped_draws": 75,
          "coverage_status": "rated",
          "distinct_rated_opponents": 48,
          "draws": 75,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "enabled",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "xiaomi/mimo-v2.5-pro",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 25,
          "model": "xiaomi/mimo-v2.5-pro",
          "point_rating_method": "sequential_elo",
          "public_id": "E-bd1bb7ac29877b8f",
          "rated_matches": 102,
          "raw_elo_rating": 1367.9946417839965,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "toggle",
          "reasoning_setting": "enabled",
          "repair_status": "repaired",
          "score": 29.00219316035198,
          "uncertainty": 5.516463908214657,
          "unilateral_faults": 0,
          "wins": 2
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 80,
          "capped_draws": 64,
          "coverage_status": "rated",
          "distinct_rated_opponents": 40,
          "draws": 64,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "z-ai/glm-5.2",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-11T14:00:45Z",
          "losses": 13,
          "model": "z-ai/glm-5.2",
          "point_rating_method": "sequential_elo",
          "public_id": "E-6a361d88d8c1fb48",
          "rated_matches": 80,
          "raw_elo_rating": 1412.8311491297252,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "first_pass",
          "score": 33.0266237531847,
          "uncertainty": 11.805555555555554,
          "unilateral_faults": 0,
          "wins": 3
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 70,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 35,
          "draws": 0,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "z-ai/glm-5.2",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 18,
          "model": "z-ai/glm-5.2",
          "point_rating_method": "sequential_elo",
          "public_id": "E-97efd9455394f6d7",
          "rated_matches": 70,
          "raw_elo_rating": 1760.0879406666484,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "repaired",
          "score": 67.82932381706101,
          "uncertainty": 15.58908290969266,
          "unilateral_faults": 0,
          "wins": 52
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 78,
          "capped_draws": 66,
          "coverage_status": "rated",
          "distinct_rated_opponents": 39,
          "draws": 66,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "z-ai/glm-5.2",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-11T17:22:09Z",
          "losses": 11,
          "model": "z-ai/glm-5.2",
          "point_rating_method": "sequential_elo",
          "public_id": "E-da1e9a6be31e371f",
          "rated_matches": 78,
          "raw_elo_rating": 1412.1516499621744,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "repaired",
          "score": 32.90140047086365,
          "uncertainty": 12.5043950463012,
          "unilateral_faults": 0,
          "wins": 1
        }
      ]
    }
  }
}