{
  "benchmark_line": "gamebench2",
  "generated_at": "2026-08-07T12:33:34Z",
  "public_release_id": "gb2-20260807-e64919171e70",
  "results_cut_id": "gb2-20260807-e64919171e70",
  "schema_version": 2,
  "snapshot_id": "20260807_123334",
  "tracks": {
    "full_freedom/balanced": {
      "GB2-01": [
        {
          "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": "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": 25,
          "model": "claude-fable-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-2dbc6efbd7db03b5",
          "rated_matches": 84,
          "raw_elo_rating": 1753.8905307528914,
          "reasoning": "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": 73.22615883803878,
          "uncertainty": 10.482614454664043,
          "unilateral_faults": 2,
          "wins": 59
        },
        {
          "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": "legacy_shared_thinking_budget",
          "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": 84,
          "capped_draws": 21,
          "coverage_status": "rated",
          "distinct_rated_opponents": 42,
          "draws": 21,
          "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": 21,
          "model": "claude-opus-4-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-829b603611fbdcef",
          "rated_matches": 84,
          "raw_elo_rating": 1645.6640036153567,
          "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": 61.59904938707476,
          "uncertainty": 10.482614454664043,
          "unilateral_faults": 0,
          "wins": 42
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 94,
          "capped_draws": 17,
          "coverage_status": "rated",
          "distinct_rated_opponents": 47,
          "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": 1492.718192054946,
          "reasoning": "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": 45.419750227325316,
          "uncertainty": 7.54891760425771,
          "unilateral_faults": 0,
          "wins": 38
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 112,
          "capped_draws": 14,
          "coverage_status": "rated",
          "distinct_rated_opponents": 56,
          "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": 37,
          "model": "claude-opus-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-0437af9582860271",
          "rated_matches": 112,
          "raw_elo_rating": 1625.1581916227758,
          "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": 60.014566638961284,
          "uncertainty": 3.286043419179858,
          "unilateral_faults": 0,
          "wins": 61
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 90,
          "capped_draws": 5,
          "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-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": 22,
          "model": "claude-opus-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-93a6875407c22137",
          "rated_matches": 90,
          "raw_elo_rating": 1808.2672310050016,
          "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": 79.22429807940591,
          "uncertainty": 8.664241836095918,
          "unilateral_faults": 0,
          "wins": 63
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 96,
          "capped_draws": 9,
          "coverage_status": "rated",
          "distinct_rated_opponents": 48,
          "draws": 9,
          "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-cd50a27a6bb44b58",
          "rated_matches": 96,
          "raw_elo_rating": 1561.2086367687052,
          "reasoning": "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": 52.82357979001043,
          "uncertainty": 7.017308256680951,
          "unilateral_faults": 0,
          "wins": 49
        },
        {
          "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": 1195.7426647399404,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "repaired",
          "score": 13.026460083495424,
          "uncertainty": 13.230288229818967,
          "unilateral_faults": 0,
          "wins": 7
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 72,
          "capped_draws": 11,
          "coverage_status": "rated",
          "distinct_rated_opponents": 36,
          "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": "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": 37,
          "model": "deepseek/deepseek-v4-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-fd9da5310ad15cac",
          "rated_matches": 72,
          "raw_elo_rating": 1569.8814747721583,
          "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": 53.08896375542971,
          "uncertainty": 14.770573598065289,
          "unilateral_faults": 0,
          "wins": 24
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 104,
          "capped_draws": 44,
          "coverage_status": "rated",
          "distinct_rated_opponents": 52,
          "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": 1468.2228066206737,
          "reasoning": "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": 43.00333801213897,
          "uncertainty": 5.045003647426665,
          "unilateral_faults": 0,
          "wins": 22
        },
        {
          "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": "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": 9,
          "model": "google/gemini-3.5-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-22f31826bcf76511",
          "rated_matches": 84,
          "raw_elo_rating": 1939.5874331556233,
          "reasoning": "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": 93.17614952930187,
          "uncertainty": 10.482614454664043,
          "unilateral_faults": 0,
          "wins": 75
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 54,
          "capped_draws": 11,
          "coverage_status": "rated",
          "distinct_rated_opponents": 27,
          "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-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": 19,
          "model": "google/gemini-3.5-flash-lite",
          "point_rating_method": "sequential_elo",
          "public_id": "E-4b4f303670ce9fb6",
          "rated_matches": 54,
          "raw_elo_rating": 1526.0634598251338,
          "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": 47.6165862588399,
          "uncertainty": 23.66998624632421,
          "unilateral_faults": 0,
          "wins": 24
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 130,
          "capped_draws": 36,
          "coverage_status": "rated",
          "distinct_rated_opponents": 65,
          "draws": 36,
          "evaluated_setting_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": 42,
          "model": "google/gemini-3.5-flash-lite",
          "point_rating_method": "sequential_elo",
          "public_id": "E-77d8df8cd762fd09",
          "rated_matches": 130,
          "raw_elo_rating": 1467.128815452549,
          "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": 43.324976491572706,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 52
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 68,
          "capped_draws": 43,
          "coverage_status": "rated",
          "distinct_rated_opponents": 34,
          "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": "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-27590b9ddebe06e6",
          "rated_matches": 68,
          "raw_elo_rating": 1513.6374207779388,
          "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": 46.90275881983249,
          "uncertainty": 16.4429265428846,
          "unilateral_faults": 0,
          "wins": 16
        },
        {
          "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": "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": 96,
          "raw_elo_rating": 1982.7510820098178,
          "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": 98.1111842126933,
          "uncertainty": 7.017308256680951,
          "unilateral_faults": 0,
          "wins": 85
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 92,
          "capped_draws": 17,
          "coverage_status": "rated",
          "distinct_rated_opponents": 46,
          "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": 53,
          "model": "gpt-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-adee794ecd761044",
          "rated_matches": 92,
          "raw_elo_rating": 1309.3826997250194,
          "reasoning": "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": 25.676297098775773,
          "uncertainty": 8.09758473652126,
          "unilateral_faults": 0,
          "wins": 22
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 84,
          "capped_draws": 19,
          "coverage_status": "rated",
          "distinct_rated_opponents": 41,
          "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": 82,
          "raw_elo_rating": 1700.0514577525005,
          "reasoning": "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": 67.38623768514597,
          "uncertainty": 11.132129994845172,
          "unilateral_faults": 2,
          "wins": 47
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 98,
          "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": 96,
          "raw_elo_rating": 1613.2596975548165,
          "reasoning": "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": 58.415585713195995,
          "uncertainty": 7.017308256680951,
          "unilateral_faults": 2,
          "wins": 53
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 108,
          "capped_draws": 22,
          "coverage_status": "rated",
          "distinct_rated_opponents": 54,
          "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": 1354.2534740561925,
          "reasoning": "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": 30.836930179581895,
          "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": 1073.351028200554,
          "reasoning": "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": 104,
          "capped_draws": 61,
          "coverage_status": "rated",
          "distinct_rated_opponents": 52,
          "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-5.5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_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": 104,
          "raw_elo_rating": 1626.375137598157,
          "reasoning": "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": 59.9941304808233,
          "uncertainty": 5.045003647426665,
          "unilateral_faults": 0,
          "wins": 29
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 88,
          "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": 28,
          "model": "gpt-5.6-luna",
          "point_rating_method": "sequential_elo",
          "public_id": "E-4f775a5b7b265dae",
          "rated_matches": 88,
          "raw_elo_rating": 1684.1296139952278,
          "reasoning": "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": 65.83747645882278,
          "uncertainty": 9.249894000318006,
          "unilateral_faults": 0,
          "wins": 51
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 98,
          "capped_draws": 1,
          "coverage_status": "rated",
          "distinct_rated_opponents": 49,
          "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": 98,
          "raw_elo_rating": 1664.1747525619378,
          "reasoning": "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": 63.92984534569066,
          "uncertainty": 6.501890762960602,
          "unilateral_faults": 0,
          "wins": 60
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 96,
          "capped_draws": 34,
          "coverage_status": "rated",
          "distinct_rated_opponents": 48,
          "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": 29,
          "model": "gpt-5.6-terra",
          "point_rating_method": "sequential_elo",
          "public_id": "E-46de264ad4571b48",
          "rated_matches": 96,
          "raw_elo_rating": 1507.6320452094085,
          "reasoning": "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": 47.06768139295753,
          "uncertainty": 7.017308256680951,
          "unilateral_faults": 0,
          "wins": 33
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 32,
          "capped_draws": 8,
          "coverage_status": "under_covered",
          "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": 1346.4764112408,
          "reasoning": "enabled",
          "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": 26.399285056998398,
          "uncertainty": 46.05265101338746,
          "unilateral_faults": 0,
          "wins": 3
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 60,
          "capped_draws": 4,
          "coverage_status": "rated",
          "distinct_rated_opponents": 30,
          "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": "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": 45,
          "model": "minimax/minimax-m3",
          "point_rating_method": "sequential_elo",
          "public_id": "E-e0a841a9daa66219",
          "rated_matches": 60,
          "raw_elo_rating": 1270.7648026910003,
          "reasoning": "enabled",
          "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": 20.481415371098425,
          "uncertainty": 20.268439966447993,
          "unilateral_faults": 0,
          "wins": 11
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 62,
          "capped_draws": 2,
          "coverage_status": "rated",
          "distinct_rated_opponents": 31,
          "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": "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": 34,
          "model": "moonshotai/kimi-k2.7-code",
          "point_rating_method": "sequential_elo",
          "public_id": "E-4935e918b1e70ea1",
          "rated_matches": 62,
          "raw_elo_rating": 1480.7658314862003,
          "reasoning": "enabled",
          "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": 43.13051350484086,
          "uncertainty": 19.244078834871203,
          "unilateral_faults": 0,
          "wins": 26
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 34,
          "capped_draws": 4,
          "coverage_status": "under_covered",
          "distinct_rated_opponents": 13,
          "draws": 4,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "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-58aadd759ee9fa72",
          "rated_matches": 26,
          "raw_elo_rating": 1550.9709158159071,
          "reasoning": "high",
          "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": 47.816778042525385,
          "uncertainty": 52.475044864937615,
          "unilateral_faults": 0,
          "wins": 12
        },
        {
          "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": "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": 94,
          "raw_elo_rating": 1525.958621253768,
          "reasoning": "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": 48.990872009700986,
          "uncertainty": 7.54891760425771,
          "unilateral_faults": 0,
          "wins": 38
        },
        {
          "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": 1494.2465984289327,
          "reasoning": "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": 45.6739398929183,
          "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": 1456.6726793206537,
          "reasoning": "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": 41.54726967322666,
          "uncertainty": 7.54891760425771,
          "unilateral_faults": 0,
          "wins": 27
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 20,
          "capped_draws": 2,
          "coverage_status": "under_covered",
          "distinct_rated_opponents": 10,
          "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": "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": 8,
          "model": "poolside/laguna-s-2.1",
          "point_rating_method": "sequential_elo",
          "public_id": "E-ffd72d2c5c11728a",
          "rated_matches": 20,
          "raw_elo_rating": 1478.3465273519382,
          "reasoning": "enabled",
          "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": 38.90719040535941,
          "uncertainty": 65.3589451179962,
          "unilateral_faults": 0,
          "wins": 10
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 58,
          "capped_draws": 11,
          "coverage_status": "rated",
          "distinct_rated_opponents": 29,
          "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": "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": 40,
          "model": "qwen/qwen3.7-max",
          "point_rating_method": "sequential_elo",
          "public_id": "E-24581eb49b81bf8f",
          "rated_matches": 58,
          "raw_elo_rating": 1316.8370332315765,
          "reasoning": "enabled",
          "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": 25.33861739757424,
          "uncertainty": 21.344455490411935,
          "unilateral_faults": 0,
          "wins": 7
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 56,
          "capped_draws": 7,
          "coverage_status": "rated",
          "distinct_rated_opponents": 28,
          "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": "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": 21,
          "model": "qwen/qwen3.7-plus",
          "point_rating_method": "sequential_elo",
          "public_id": "E-1e5dceaf2ba3ca9a",
          "rated_matches": 56,
          "raw_elo_rating": 1548.1271187402674,
          "reasoning": "enabled",
          "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": 50.0895189502136,
          "uncertainty": 22.47661785325219,
          "unilateral_faults": 0,
          "wins": 28
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 54,
          "capped_draws": 13,
          "coverage_status": "rated",
          "distinct_rated_opponents": 27,
          "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",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "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": "thinkingmachines/inkling",
          "point_rating_method": "sequential_elo",
          "public_id": "E-46c7f693daaae605",
          "rated_matches": 54,
          "raw_elo_rating": 1407.8495385633466,
          "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": 34.916500267983515,
          "uncertainty": 23.66998624632421,
          "unilateral_faults": 0,
          "wins": 14
        },
        {
          "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": 1799.055667309865,
          "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": 78.50521178364832,
          "uncertainty": 5.516463908214657,
          "unilateral_faults": 2,
          "wins": 73
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 62,
          "capped_draws": 10,
          "coverage_status": "rated",
          "distinct_rated_opponents": 31,
          "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": "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": 30,
          "model": "x-ai/grok-build-0.1",
          "point_rating_method": "sequential_elo",
          "public_id": "E-f1ded648f3ab17dc",
          "rated_matches": 62,
          "raw_elo_rating": 1482.4848219509731,
          "reasoning": "enabled",
          "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": 43.3151899497727,
          "uncertainty": 19.244078834871203,
          "unilateral_faults": 0,
          "wins": 22
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 62,
          "capped_draws": 3,
          "coverage_status": "rated",
          "distinct_rated_opponents": 31,
          "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": 34,
          "model": "xiaomi/mimo-v2.5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-1208f50b0908ecb4",
          "rated_matches": 62,
          "raw_elo_rating": 1399.8536397077935,
          "reasoning": "enabled",
          "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": 34.43786730610081,
          "uncertainty": 19.244078834871203,
          "unilateral_faults": 0,
          "wins": 25
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 50,
          "capped_draws": 3,
          "coverage_status": "rated",
          "distinct_rated_opponents": 25,
          "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": "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": 34,
          "model": "xiaomi/mimo-v2.5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-2a71bee21bd7c0b9",
          "rated_matches": 50,
          "raw_elo_rating": 1401.127265205498,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "repaired",
          "score": 33.97135904113655,
          "uncertainty": 26.264004201400486,
          "unilateral_faults": 0,
          "wins": 13
        },
        {
          "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": 1469.1718670852033,
          "reasoning": "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": 42.524252957277774,
          "uncertainty": 11.805555555555554,
          "unilateral_faults": 0,
          "wins": 43
        }
      ],
      "GB2-02": [
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 78,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 38,
          "draws": 30,
          "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": 76,
          "raw_elo_rating": 1690.47443747152,
          "reasoning": "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": 72.88223492302193,
          "uncertainty": 13.230288229818967,
          "unilateral_faults": 2,
          "wins": 37
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 60,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 30,
          "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-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": 4,
          "model": "claude-opus-4-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-03472a04778e9928",
          "rated_matches": 60,
          "raw_elo_rating": 1499.262611968492,
          "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": 28.065418891234213,
          "uncertainty": 20.268439966447993,
          "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": "legacy_shared_thinking_budget",
          "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": 1459.9363913520322,
          "reasoning": "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": 20.525841154304743,
          "uncertainty": 12.5043950463012,
          "unilateral_faults": 0,
          "wins": 1
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 72,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 36,
          "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-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-50b401cafe71e710",
          "rated_matches": 72,
          "raw_elo_rating": 1653.2897177516088,
          "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": 64.13551289470387,
          "uncertainty": 14.770573598065289,
          "unilateral_faults": 0,
          "wins": 33
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 72,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 36,
          "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-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": 72,
          "raw_elo_rating": 1649.7760660413985,
          "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": 63.33552912707279,
          "uncertainty": 14.770573598065289,
          "unilateral_faults": 0,
          "wins": 32
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 76,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 38,
          "draws": 71,
          "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": 76,
          "raw_elo_rating": 1487.86953058894,
          "reasoning": "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": 26.753406537020762,
          "uncertainty": 13.230288229818967,
          "unilateral_faults": 0,
          "wins": 1
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 64,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 32,
          "draws": 54,
          "evaluated_setting_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": 10,
          "model": "deepseek/deepseek-v4-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-08e2baea96c43eb4",
          "rated_matches": 64,
          "raw_elo_rating": 1444.9368175852394,
          "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": 16.06107223859427,
          "uncertainty": 18.26736729460423,
          "unilateral_faults": 0,
          "wins": 0
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 68,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 34,
          "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": "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": 68,
          "raw_elo_rating": 1488.5381352612483,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "repaired",
          "score": 26.320474066181795,
          "uncertainty": 16.4429265428846,
          "unilateral_faults": 0,
          "wins": 2
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 90,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 45,
          "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",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_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": 90,
          "raw_elo_rating": 1495.3389302620424,
          "reasoning": "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": 29.285703310875242,
          "uncertainty": 8.664241836095918,
          "unilateral_faults": 0,
          "wins": 10
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 36,
          "capped_draws": 0,
          "coverage_status": "under_covered",
          "distinct_rated_opponents": 18,
          "draws": 36,
          "evaluated_setting_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": 0,
          "model": "google/gemini-3.5-flash-lite",
          "point_rating_method": "sequential_elo",
          "public_id": "E-dbbc5835674b5f2c",
          "rated_matches": 36,
          "raw_elo_rating": 1494.8163977249776,
          "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": 23.741559061870756,
          "uncertainty": 38.449493652678655,
          "unilateral_faults": 0,
          "wins": 0
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 86,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 43,
          "draws": 80,
          "evaluated_setting_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": 86,
          "raw_elo_rating": 1464.156172217111,
          "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": 21.969050080927598,
          "uncertainty": 9.855626741889738,
          "unilateral_faults": 0,
          "wins": 1
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 80,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 40,
          "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": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_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": 80,
          "raw_elo_rating": 1471.4974252789027,
          "reasoning": "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": 23.285331416066995,
          "uncertainty": 11.805555555555554,
          "unilateral_faults": 0,
          "wins": 4
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 90,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 45,
          "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": 1478.9493057309376,
          "reasoning": "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": 25.554134372396923,
          "uncertainty": 8.664241836095918,
          "unilateral_faults": 0,
          "wins": 3
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 78,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 39,
          "draws": 75,
          "evaluated_setting_identity": {
            "canonical_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": 78,
          "raw_elo_rating": 1482.129902029356,
          "reasoning": "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": 25.578831533804646,
          "uncertainty": 12.5043950463012,
          "unilateral_faults": 0,
          "wins": 0
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 72,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 36,
          "draws": 43,
          "evaluated_setting_identity": {
            "canonical_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": 72,
          "raw_elo_rating": 1580.4346988559294,
          "reasoning": "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": 47.54797454033727,
          "uncertainty": 14.770573598065289,
          "unilateral_faults": 0,
          "wins": 20
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 70,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 35,
          "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-5.6-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": 70,
          "raw_elo_rating": 1473.5711246807089,
          "reasoning": "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": 23.068325697614167,
          "uncertainty": 15.58908290969266,
          "unilateral_faults": 0,
          "wins": 0
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 76,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 38,
          "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-5.6-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-087d760c91df7f17",
          "rated_matches": 76,
          "raw_elo_rating": 1582.2391207094831,
          "reasoning": "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": 48.239355196944736,
          "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": 75,
          "evaluated_setting_identity": {
            "canonical_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": 84,
          "raw_elo_rating": 1484.6607459565766,
          "reasoning": "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": 26.523304025075756,
          "uncertainty": 10.482614454664043,
          "unilateral_faults": 0,
          "wins": 0
        },
        {
          "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": 1444.502691239462,
          "reasoning": "enabled",
          "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": 8.268540367052571,
          "uncertainty": 60.5072070285374,
          "unilateral_faults": 0,
          "wins": 0
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 16,
          "capped_draws": 0,
          "coverage_status": "under_covered",
          "distinct_rated_opponents": 8,
          "draws": 16,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "enabled",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "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": 0,
          "model": "meituan/longcat-2.0",
          "point_rating_method": "sequential_elo",
          "public_id": "E-a00d8e3eb7dd07cf",
          "rated_matches": 16,
          "raw_elo_rating": 1493.6506550614847,
          "reasoning": "enabled",
          "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": 16.36012399547446,
          "uncertainty": 77.5178125181665,
          "unilateral_faults": 0,
          "wins": 0
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 48,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 24,
          "draws": 37,
          "evaluated_setting_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": 11,
          "model": "minimax/minimax-m3",
          "point_rating_method": "sequential_elo",
          "public_id": "E-cad87bcb23d33fef",
          "rated_matches": 48,
          "raw_elo_rating": 1423.4954691324942,
          "reasoning": "enabled",
          "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": 9.465148378582635,
          "uncertainty": 27.678571428571434,
          "unilateral_faults": 0,
          "wins": 0
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 58,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 29,
          "draws": 49,
          "evaluated_setting_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": 7,
          "model": "moonshotai/kimi-k2.7-code",
          "point_rating_method": "sequential_elo",
          "public_id": "E-85c8a9372a607001",
          "rated_matches": 58,
          "raw_elo_rating": 1474.266865658278,
          "reasoning": "enabled",
          "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": 22.17843037435877,
          "uncertainty": 21.344455490411935,
          "unilateral_faults": 0,
          "wins": 2
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 24,
          "capped_draws": 0,
          "coverage_status": "under_covered",
          "distinct_rated_opponents": 12,
          "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": 4,
          "model": "moonshotai/kimi-k3",
          "point_rating_method": "sequential_elo",
          "public_id": "E-0c4144684fc36307",
          "rated_matches": 24,
          "raw_elo_rating": 1529.971155279276,
          "reasoning": "high",
          "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": 28.503312323598145,
          "uncertainty": 56.25,
          "unilateral_faults": 0,
          "wins": 4
        },
        {
          "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": "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": 88,
          "raw_elo_rating": 1463.2953460829026,
          "reasoning": "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": 21.883388248077022,
          "uncertainty": 9.249894000318006,
          "unilateral_faults": 0,
          "wins": 1
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 84,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 42,
          "draws": 75,
          "evaluated_setting_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": 84,
          "raw_elo_rating": 1482.281346131285,
          "reasoning": "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": 25.98156528887542,
          "uncertainty": 10.482614454664043,
          "unilateral_faults": 0,
          "wins": 4
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 16,
          "capped_draws": 0,
          "coverage_status": "under_covered",
          "distinct_rated_opponents": 7,
          "draws": 14,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "enabled",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "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": 0,
          "model": "poolside/laguna-s-2.1",
          "point_rating_method": "sequential_elo",
          "public_id": "E-7164ee63b9dd911a",
          "rated_matches": 14,
          "raw_elo_rating": 1497.5699603018195,
          "reasoning": "enabled",
          "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": 15.825989542536085,
          "uncertainty": 85.34944487358055,
          "unilateral_faults": 0,
          "wins": 0
        },
        {
          "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": "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": 0,
          "model": "poolside/laguna-s-2.1",
          "point_rating_method": "sequential_elo",
          "public_id": "E-ba56689188a301b2",
          "rated_matches": 18,
          "raw_elo_rating": 1492.882725737239,
          "reasoning": "enabled",
          "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": 17.380130896494958,
          "uncertainty": 70.95786693528086,
          "unilateral_faults": 0,
          "wins": 0
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 48,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 24,
          "draws": 44,
          "evaluated_setting_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": 1,
          "model": "qwen/qwen3.7-max",
          "point_rating_method": "sequential_elo",
          "public_id": "E-95265340f8562bfd",
          "rated_matches": 48,
          "raw_elo_rating": 1498.2890155617906,
          "reasoning": "enabled",
          "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": 26.49404822461132,
          "uncertainty": 27.678571428571434,
          "unilateral_faults": 0,
          "wins": 3
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 54,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 27,
          "draws": 49,
          "evaluated_setting_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": 54,
          "raw_elo_rating": 1487.9660769853413,
          "reasoning": "enabled",
          "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": 24.87387032897688,
          "uncertainty": 23.66998624632421,
          "unilateral_faults": 0,
          "wins": 1
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 84,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 42,
          "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": "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": 84,
          "raw_elo_rating": 1483.647195989816,
          "reasoning": "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": 26.292540253374842,
          "uncertainty": 10.482614454664043,
          "unilateral_faults": 0,
          "wins": 1
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 96,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 48,
          "draws": 67,
          "evaluated_setting_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": 96,
          "raw_elo_rating": 1499.1232344259092,
          "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": 30.44728628591251,
          "uncertainty": 7.017308256680951,
          "unilateral_faults": 0,
          "wins": 13
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 54,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 27,
          "draws": 49,
          "evaluated_setting_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": 54,
          "raw_elo_rating": 1482.2015752361406,
          "reasoning": "enabled",
          "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": 23.56141587754649,
          "uncertainty": 23.66998624632421,
          "unilateral_faults": 0,
          "wins": 2
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 50,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 25,
          "draws": 45,
          "evaluated_setting_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": 3,
          "model": "xiaomi/mimo-v2.5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-5b213ae773e821cc",
          "rated_matches": 50,
          "raw_elo_rating": 1490.3044220858997,
          "reasoning": "enabled",
          "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": 24.93377960152974,
          "uncertainty": 26.264004201400486,
          "unilateral_faults": 0,
          "wins": 2
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 46,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 23,
          "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": "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": 3,
          "model": "xiaomi/mimo-v2.5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-a5f372b0e5962ee5",
          "rated_matches": 46,
          "raw_elo_rating": 1466.195547247045,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "repaired",
          "score": 18.913118772607746,
          "uncertainty": 29.182495748947275,
          "unilateral_faults": 0,
          "wins": 0
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 46,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 23,
          "draws": 39,
          "evaluated_setting_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": 5,
          "model": "xiaomi/mimo-v2.5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-c37f25e181320efb",
          "rated_matches": 46,
          "raw_elo_rating": 1486.8182780372601,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "repaired",
          "score": 23.608475978461932,
          "uncertainty": 29.182495748947275,
          "unilateral_faults": 0,
          "wins": 2
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 62,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 31,
          "draws": 61,
          "evaluated_setting_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": 62,
          "raw_elo_rating": 1475.841977949159,
          "reasoning": "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": 22.919618819874938,
          "uncertainty": 19.244078834871203,
          "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": "legacy_shared_thinking_budget",
          "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": 68,
          "capped_draws": 10,
          "coverage_status": "rated",
          "distinct_rated_opponents": 34,
          "draws": 34,
          "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": 22,
          "model": "claude-opus-4-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-dfb18dba94eee30b",
          "rated_matches": 68,
          "raw_elo_rating": 1438.7975158584218,
          "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": 30.81671727920589,
          "uncertainty": 16.4429265428846,
          "unilateral_faults": 0,
          "wins": 12
        },
        {
          "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": 1449.778133454939,
          "reasoning": "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": 32.26904479710366,
          "uncertainty": 18.26736729460423,
          "unilateral_faults": 0,
          "wins": 11
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 78,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 39,
          "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": 78,
          "raw_elo_rating": 1840.6237701972532,
          "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": 92.59125164361666,
          "uncertainty": 12.5043950463012,
          "unilateral_faults": 0,
          "wins": 64
        },
        {
          "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": 5,
          "model": "claude-opus-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-d8babc5495b1a188",
          "rated_matches": 80,
          "raw_elo_rating": 1881.3828904374436,
          "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": 98.89386033488782,
          "uncertainty": 11.805555555555554,
          "unilateral_faults": 0,
          "wins": 71
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 32,
          "capped_draws": 1,
          "coverage_status": "under_covered",
          "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": 1392.6036728774286,
          "reasoning": "enabled",
          "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": 20.494361273200912,
          "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": 1524.4985638630642,
          "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": 43.00749050094252,
          "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": 1571.8753694864479,
          "reasoning": "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": 51.11619311992135,
          "uncertainty": 16.4429265428846,
          "unilateral_faults": 0,
          "wins": 23
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 52,
          "capped_draws": 2,
          "coverage_status": "rated",
          "distinct_rated_opponents": 26,
          "draws": 19,
          "evaluated_setting_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": 22,
          "model": "google/gemini-3.5-flash-lite",
          "point_rating_method": "sequential_elo",
          "public_id": "E-c7e8525629d5d658",
          "rated_matches": 52,
          "raw_elo_rating": 1450.3211376075822,
          "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": 31.53879375886739,
          "uncertainty": 24.930281974344517,
          "unilateral_faults": 0,
          "wins": 11
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 52,
          "capped_draws": 6,
          "coverage_status": "rated",
          "distinct_rated_opponents": 26,
          "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-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-d9a1854998f1794f",
          "rated_matches": 52,
          "raw_elo_rating": 1419.4269463569747,
          "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": 26.82624488756462,
          "uncertainty": 24.930281974344517,
          "unilateral_faults": 0,
          "wins": 7
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 50,
          "capped_draws": 1,
          "coverage_status": "rated",
          "distinct_rated_opponents": 25,
          "draws": 14,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "google/gemini-3.6-flash",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 16,
          "model": "google/gemini-3.6-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-1d4a922c11c37a8d",
          "rated_matches": 50,
          "raw_elo_rating": 1516.2025080152273,
          "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": 41.425474084503904,
          "uncertainty": 26.264004201400486,
          "unilateral_faults": 0,
          "wins": 20
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 45,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 23,
          "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": "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": 20,
          "model": "google/gemini-3.6-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-2e4f025f94dafe33",
          "rated_matches": 45,
          "raw_elo_rating": 1432.79675175012,
          "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": 28.250533342732655,
          "uncertainty": 29.97097807744857,
          "unilateral_faults": 0,
          "wins": 12
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 62,
          "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": 62,
          "raw_elo_rating": 1399.3895422530882,
          "reasoning": "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": 24.46366360644326,
          "uncertainty": 19.244078834871203,
          "unilateral_faults": 0,
          "wins": 8
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 78,
          "capped_draws": 2,
          "coverage_status": "rated",
          "distinct_rated_opponents": 39,
          "draws": 36,
          "evaluated_setting_identity": {
            "canonical_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": 24,
          "model": "gpt-5.4",
          "point_rating_method": "sequential_elo",
          "public_id": "E-496f83ad0bd69447",
          "rated_matches": 78,
          "raw_elo_rating": 1439.39286064408,
          "reasoning": "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": 31.388151856713836,
          "uncertainty": 12.5043950463012,
          "unilateral_faults": 0,
          "wins": 18
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 83,
          "capped_draws": 11,
          "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-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": 20,
          "model": "gpt-5.4-mini",
          "point_rating_method": "sequential_elo",
          "public_id": "E-9e39bdd48b7328c7",
          "rated_matches": 83,
          "raw_elo_rating": 1485.5548858435868,
          "reasoning": "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": 38.63707357709248,
          "uncertainty": 10.804472558998102,
          "unilateral_faults": 0,
          "wins": 15
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 74,
          "capped_draws": 7,
          "coverage_status": "rated",
          "distinct_rated_opponents": 37,
          "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-5.5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_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": 74,
          "raw_elo_rating": 1440.3708349548044,
          "reasoning": "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": 31.35664793074286,
          "uncertainty": 13.985026918962571,
          "unilateral_faults": 0,
          "wins": 15
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 70,
          "capped_draws": 13,
          "coverage_status": "rated",
          "distinct_rated_opponents": 35,
          "draws": 42,
          "evaluated_setting_identity": {
            "canonical_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": 70,
          "raw_elo_rating": 1449.241069098968,
          "reasoning": "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": 32.513954746621025,
          "uncertainty": 15.58908290969266,
          "unilateral_faults": 0,
          "wins": 11
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 58,
          "capped_draws": 2,
          "coverage_status": "rated",
          "distinct_rated_opponents": 29,
          "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": 58,
          "raw_elo_rating": 1545.0279839646837,
          "reasoning": "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": 46.42280040640819,
          "uncertainty": 21.344455490411935,
          "unilateral_faults": 0,
          "wins": 29
        },
        {
          "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": 1484.2886571135925,
          "reasoning": "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": 38.23648244618929,
          "uncertainty": 12.5043950463012,
          "unilateral_faults": 0,
          "wins": 14
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 32,
          "capped_draws": 2,
          "coverage_status": "under_covered",
          "distinct_rated_opponents": 16,
          "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": "meituan/longcat-2.0",
            "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 7,
          "model": "meituan/longcat-2.0",
          "point_rating_method": "sequential_elo",
          "public_id": "E-d3a5befe76215b48",
          "rated_matches": 32,
          "raw_elo_rating": 1523.8698064263606,
          "reasoning": "enabled",
          "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": 40.517480327470835,
          "uncertainty": 43.288827977848925,
          "unilateral_faults": 0,
          "wins": 12
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 34,
          "capped_draws": 1,
          "coverage_status": "under_covered",
          "distinct_rated_opponents": 17,
          "draws": 14,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "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": 6,
          "model": "moonshotai/kimi-k3",
          "point_rating_method": "sequential_elo",
          "public_id": "E-980b1f419104e27a",
          "rated_matches": 34,
          "raw_elo_rating": 1597.8931533577227,
          "reasoning": "high",
          "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": 52.11681184018075,
          "uncertainty": 40.76542547285167,
          "unilateral_faults": 0,
          "wins": 14
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 36,
          "capped_draws": 2,
          "coverage_status": "under_covered",
          "distinct_rated_opponents": 18,
          "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": "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": 13,
          "model": "nex-agi/nex-n2-pro",
          "point_rating_method": "sequential_elo",
          "public_id": "E-57ad2863cbf32d58",
          "rated_matches": 36,
          "raw_elo_rating": 1436.5490406123818,
          "reasoning": "enabled",
          "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": 27.788262281969292,
          "uncertainty": 38.449493652678655,
          "unilateral_faults": 0,
          "wins": 5
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 62,
          "capped_draws": 8,
          "coverage_status": "rated",
          "distinct_rated_opponents": 31,
          "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": 11,
          "model": "openai/gpt-oss-120b",
          "point_rating_method": "sequential_elo",
          "public_id": "E-87b4bd61da369b42",
          "rated_matches": 62,
          "raw_elo_rating": 1430.255627323167,
          "reasoning": "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": 29.171925207422163,
          "uncertainty": 19.244078834871203,
          "unilateral_faults": 0,
          "wins": 8
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 26,
          "capped_draws": 1,
          "coverage_status": "under_covered",
          "distinct_rated_opponents": 13,
          "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": "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-08762a3df1a52f6b",
          "rated_matches": 26,
          "raw_elo_rating": 1462.487607959199,
          "reasoning": "enabled",
          "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": 30.033340953329773,
          "uncertainty": 52.475044864937615,
          "unilateral_faults": 0,
          "wins": 3
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 26,
          "capped_draws": 2,
          "coverage_status": "under_covered",
          "distinct_rated_opponents": 13,
          "draws": 6,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "enabled",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "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": 11,
          "model": "poolside/laguna-s-2.1",
          "point_rating_method": "sequential_elo",
          "public_id": "E-936fb7956df3d03b",
          "rated_matches": 26,
          "raw_elo_rating": 1506.5582599696256,
          "reasoning": "enabled",
          "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": 36.7558053708189,
          "uncertainty": 52.475044864937615,
          "unilateral_faults": 0,
          "wins": 9
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 46,
          "capped_draws": 2,
          "coverage_status": "rated",
          "distinct_rated_opponents": 23,
          "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": "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": 14,
          "model": "thinkingmachines/inkling",
          "point_rating_method": "sequential_elo",
          "public_id": "E-77829668b3641188",
          "rated_matches": 46,
          "raw_elo_rating": 1607.1778209283398,
          "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": 54.946552450271184,
          "uncertainty": 29.182495748947275,
          "unilateral_faults": 0,
          "wins": 24
        },
        {
          "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": 1504.1234121905509,
          "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": 41.26204320265185,
          "uncertainty": 12.5043950463012,
          "unilateral_faults": 0,
          "wins": 24
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 36,
          "capped_draws": 0,
          "coverage_status": "under_covered",
          "distinct_rated_opponents": 18,
          "draws": 19,
          "evaluated_setting_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": 9,
          "model": "x-ai/grok-build-0.1",
          "point_rating_method": "sequential_elo",
          "public_id": "E-2a93343a8a88fd59",
          "rated_matches": 36,
          "raw_elo_rating": 1486.663450518995,
          "reasoning": "enabled",
          "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": 35.4326315397912,
          "uncertainty": 38.449493652678655,
          "unilateral_faults": 0,
          "wins": 8
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 52,
          "capped_draws": 13,
          "coverage_status": "rated",
          "distinct_rated_opponents": 26,
          "draws": 38,
          "evaluated_setting_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": 52,
          "raw_elo_rating": 1446.0068426521739,
          "reasoning": "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": 30.880698337056444,
          "uncertainty": 24.930281974344517,
          "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": 1582.9690692214492,
          "reasoning": "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": 47.83931957227835,
          "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": "legacy_shared_thinking_budget",
          "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": 52,
          "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": 1483.6856058732603,
          "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": 30.749828609175978,
          "uncertainty": 5.279033784546012,
          "unilateral_faults": 0,
          "wins": 11
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 104,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 52,
          "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": 1481.537434054386,
          "reasoning": "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": 30.39355816481966,
          "uncertainty": 5.045003647426665,
          "unilateral_faults": 0,
          "wins": 5
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 98,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 49,
          "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-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-048d3dcf802043b4",
          "rated_matches": 98,
          "raw_elo_rating": 1557.8175182985399,
          "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": 44.040583390386246,
          "uncertainty": 6.501890762960602,
          "unilateral_faults": 0,
          "wins": 17
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 100,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 50,
          "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-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": 100,
          "raw_elo_rating": 1567.7938393705367,
          "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": 45.925786860760766,
          "uncertainty": 6.001859510499461,
          "unilateral_faults": 0,
          "wins": 41
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 100,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 50,
          "draws": 70,
          "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": 100,
          "raw_elo_rating": 1488.2760299875736,
          "reasoning": "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": 31.478769660606087,
          "uncertainty": 6.001859510499461,
          "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": 1469.7658079724426,
          "reasoning": "enabled",
          "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": 26.333035635148633,
          "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": 1482.6080624665635,
          "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": 28.801808670018016,
          "uncertainty": 17.33472217815261,
          "unilateral_faults": 0,
          "wins": 4
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 90,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 44,
          "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": "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": 4,
          "model": "google/gemini-3.1-flash-lite",
          "point_rating_method": "sequential_elo",
          "public_id": "E-860c31323fa5eda7",
          "rated_matches": 88,
          "raw_elo_rating": 1505.6208754393567,
          "reasoning": "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": 34.157939951088196,
          "uncertainty": 9.249894000318006,
          "unilateral_faults": 2,
          "wins": 8
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 98,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 49,
          "draws": 56,
          "evaluated_setting_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-32cfa6c9dfb1d16f",
          "rated_matches": 98,
          "raw_elo_rating": 1556.148668508276,
          "reasoning": "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": 43.737382109924624,
          "uncertainty": 6.501890762960602,
          "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": 1503.808618075588,
          "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": 34.665054859426824,
          "uncertainty": 3.4955591261534025,
          "unilateral_faults": 0,
          "wins": 10
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 51,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 26,
          "draws": 42,
          "evaluated_setting_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": 4,
          "model": "google/gemini-3.5-flash-lite",
          "point_rating_method": "sequential_elo",
          "public_id": "E-6098de52ddfabfb1",
          "rated_matches": 50,
          "raw_elo_rating": 1511.0193759194003,
          "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": 32.66581779874579,
          "uncertainty": 26.264004201400486,
          "unilateral_faults": 0,
          "wins": 4
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 63,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 32,
          "draws": 51,
          "evaluated_setting_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-cefb1dec9ce36375",
          "rated_matches": 63,
          "raw_elo_rating": 1465.1675896513302,
          "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": 25.42746967287035,
          "uncertainty": 18.75,
          "unilateral_faults": 0,
          "wins": 5
        },
        {
          "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": 1500.520993952449,
          "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": 34.272780519974965,
          "uncertainty": 2.084924851410568,
          "unilateral_faults": 0,
          "wins": 20
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 56,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 27,
          "draws": 44,
          "evaluated_setting_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": 4,
          "model": "google/gemma-4-31b-it",
          "point_rating_method": "sequential_elo",
          "public_id": "E-62ca2464f2212fc9",
          "rated_matches": 54,
          "raw_elo_rating": 1509.1633957360891,
          "reasoning": "enabled",
          "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": 32.70564887564202,
          "uncertainty": 23.66998624632421,
          "unilateral_faults": 2,
          "wins": 6
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 96,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 48,
          "draws": 60,
          "evaluated_setting_identity": {
            "canonical_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-6f1aae863396df76",
          "rated_matches": 96,
          "raw_elo_rating": 1495.669383234101,
          "reasoning": "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": 32.67442303505885,
          "uncertainty": 7.017308256680951,
          "unilateral_faults": 0,
          "wins": 17
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 100,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 50,
          "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-5.4",
            "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": 13,
          "model": "gpt-5.4",
          "point_rating_method": "sequential_elo",
          "public_id": "E-0b4132559ee98caf",
          "rated_matches": 100,
          "raw_elo_rating": 1509.4148214952497,
          "reasoning": "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": 35.31932420897261,
          "uncertainty": 6.001859510499461,
          "unilateral_faults": 0,
          "wins": 22
        },
        {
          "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": 1561.7564985722227,
          "reasoning": "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": 44.441938728209706,
          "uncertainty": 8.664241836095918,
          "unilateral_faults": 0,
          "wins": 20
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 96,
          "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-5.4-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": 96,
          "raw_elo_rating": 1564.996519212638,
          "reasoning": "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": 45.26997029285312,
          "uncertainty": 7.017308256680951,
          "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": 1486.0440995567778,
          "reasoning": "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": 31.14381674077765,
          "uncertainty": 5.516463908214657,
          "unilateral_faults": 0,
          "wins": 22
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 96,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 48,
          "draws": 85,
          "evaluated_setting_identity": {
            "canonical_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": 96,
          "raw_elo_rating": 1508.170150760798,
          "reasoning": "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": 34.94559731506889,
          "uncertainty": 7.017308256680951,
          "unilateral_faults": 0,
          "wins": 6
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 106,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 53,
          "draws": 85,
          "evaluated_setting_identity": {
            "canonical_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": 106,
          "raw_elo_rating": 1530.4112566798308,
          "reasoning": "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": 39.33968507396859,
          "uncertainty": 4.586824452283178,
          "unilateral_faults": 0,
          "wins": 15
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 96,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 48,
          "draws": 74,
          "evaluated_setting_identity": {
            "canonical_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": 96,
          "raw_elo_rating": 1514.0428742199645,
          "reasoning": "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": 36.01257007858806,
          "uncertainty": 7.017308256680951,
          "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": 1429.7116213239594,
          "reasoning": "enabled",
          "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": 17.893598364366323,
          "uncertainty": 26.264004201400486,
          "unilateral_faults": 0,
          "wins": 4
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 24,
          "capped_draws": 0,
          "coverage_status": "under_covered",
          "distinct_rated_opponents": 12,
          "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": "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": 8,
          "model": "meituan/longcat-2.0",
          "point_rating_method": "sequential_elo",
          "public_id": "E-4ccf296e55b59be3",
          "rated_matches": 22,
          "raw_elo_rating": 1411.4338858377105,
          "reasoning": "enabled",
          "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": 9.59572803499691,
          "uncertainty": 60.5072070285374,
          "unilateral_faults": 2,
          "wins": 1
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 50,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 25,
          "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": "meituan/longcat-2.0",
            "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 13,
          "model": "meituan/longcat-2.0",
          "point_rating_method": "sequential_elo",
          "public_id": "E-9c9e87bb30b3cb99",
          "rated_matches": 50,
          "raw_elo_rating": 1412.4235384600008,
          "reasoning": "enabled",
          "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": 14.752651293120403,
          "uncertainty": 26.264004201400486,
          "unilateral_faults": 0,
          "wins": 2
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 64,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 32,
          "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": "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": 7,
          "model": "minimax/minimax-m3",
          "point_rating_method": "sequential_elo",
          "public_id": "E-c60620c3c72a6064",
          "rated_matches": 64,
          "raw_elo_rating": 1496.4810512769454,
          "reasoning": "enabled",
          "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": 31.186735485803233,
          "uncertainty": 18.26736729460423,
          "unilateral_faults": 0,
          "wins": 6
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 64,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 32,
          "draws": 52,
          "evaluated_setting_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": 7,
          "model": "moonshotai/kimi-k2.7-code",
          "point_rating_method": "sequential_elo",
          "public_id": "E-eb97811a38950c20",
          "rated_matches": 64,
          "raw_elo_rating": 1481.7071638258212,
          "reasoning": "enabled",
          "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": 28.50257444344345,
          "uncertainty": 18.26736729460423,
          "unilateral_faults": 0,
          "wins": 5
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 46,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 21,
          "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": "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": 5,
          "model": "moonshotai/kimi-k3",
          "point_rating_method": "sequential_elo",
          "public_id": "E-7c724729d138057b",
          "rated_matches": 42,
          "raw_elo_rating": 1534.645824597623,
          "reasoning": "high",
          "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": 36.0520622569886,
          "uncertainty": 32.49928516630233,
          "unilateral_faults": 0,
          "wins": 7
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 88,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 44,
          "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": 1463.6610917058263,
          "reasoning": "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": 26.534569513484524,
          "uncertainty": 9.249894000318006,
          "unilateral_faults": 0,
          "wins": 9
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 96,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 48,
          "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": 1465.1792260115858,
          "reasoning": "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": 27.134886304266157,
          "uncertainty": 7.017308256680951,
          "unilateral_faults": 0,
          "wins": 2
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 40,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 20,
          "draws": 27,
          "evaluated_setting_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": 9,
          "model": "poolside/laguna-s-2.1",
          "point_rating_method": "sequential_elo",
          "public_id": "E-e996fd38983e3b7f",
          "rated_matches": 40,
          "raw_elo_rating": 1488.1906395787857,
          "reasoning": "enabled",
          "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": 27.34486716917701,
          "uncertainty": 34.33688094430304,
          "unilateral_faults": 0,
          "wins": 4
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 64,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 32,
          "draws": 38,
          "evaluated_setting_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": 16,
          "model": "qwen/qwen3.7-max",
          "point_rating_method": "sequential_elo",
          "public_id": "E-ea08328e287de1ad",
          "rated_matches": 64,
          "raw_elo_rating": 1482.9185199612966,
          "reasoning": "enabled",
          "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": 28.722657001810248,
          "uncertainty": 18.26736729460423,
          "unilateral_faults": 0,
          "wins": 10
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 96,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 48,
          "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": "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": 96,
          "raw_elo_rating": 1524.4271477634718,
          "reasoning": "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": 37.89921383372028,
          "uncertainty": 7.017308256680951,
          "unilateral_faults": 0,
          "wins": 11
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 42,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 21,
          "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": 4,
          "model": "thinkingmachines/inkling",
          "point_rating_method": "sequential_elo",
          "public_id": "E-fce01db31ecf26d2",
          "rated_matches": 42,
          "raw_elo_rating": 1492.516457423049,
          "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": 28.397881427239696,
          "uncertainty": 32.49928516630233,
          "unilateral_faults": 0,
          "wins": 3
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 108,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 54,
          "draws": 80,
          "evaluated_setting_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": 108,
          "raw_elo_rating": 1488.922495957919,
          "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": 31.866644636143132,
          "uncertainty": 4.1413142610575715,
          "unilateral_faults": 0,
          "wins": 12
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 64,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 32,
          "draws": 56,
          "evaluated_setting_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": 5,
          "model": "x-ai/grok-build-0.1",
          "point_rating_method": "sequential_elo",
          "public_id": "E-85934b32572399da",
          "rated_matches": 64,
          "raw_elo_rating": 1474.1169273355108,
          "reasoning": "enabled",
          "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": 27.12355912625024,
          "uncertainty": 18.26736729460423,
          "unilateral_faults": 0,
          "wins": 3
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 54,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 27,
          "draws": 38,
          "evaluated_setting_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": 13,
          "model": "xiaomi/mimo-v2.5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-00e6914e513b1656",
          "rated_matches": 54,
          "raw_elo_rating": 1484.6753588209492,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "repaired",
          "score": 28.256594088339913,
          "uncertainty": 23.66998624632421,
          "unilateral_faults": 0,
          "wins": 3
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 54,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 27,
          "draws": 37,
          "evaluated_setting_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": 16,
          "model": "xiaomi/mimo-v2.5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-23e877112cb95491",
          "rated_matches": 54,
          "raw_elo_rating": 1439.2294400822045,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "repaired",
          "score": 19.999852928212512,
          "uncertainty": 23.66998624632421,
          "unilateral_faults": 0,
          "wins": 1
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 62,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 31,
          "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": "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": 9,
          "model": "xiaomi/mimo-v2.5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-2f7e15b8aa123825",
          "rated_matches": 62,
          "raw_elo_rating": 1466.7131243673532,
          "reasoning": "enabled",
          "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": 25.636454231351987,
          "uncertainty": 19.244078834871203,
          "unilateral_faults": 0,
          "wins": 3
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 60,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 30,
          "draws": 36,
          "evaluated_setting_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": 9,
          "model": "xiaomi/mimo-v2.5-pro",
          "point_rating_method": "sequential_elo",
          "public_id": "E-ffdebde8a72ed049",
          "rated_matches": 60,
          "raw_elo_rating": 1558.4476161482546,
          "reasoning": "enabled",
          "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": 42.154145305697575,
          "uncertainty": 20.268439966447993,
          "unilateral_faults": 0,
          "wins": 15
        },
        {
          "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": 1501.1308285615892,
          "reasoning": "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": 32.1670764313632,
          "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": 1673.6388165109624,
          "reasoning": "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": 58.88434592732646,
          "uncertainty": 4.586824452283178,
          "unilateral_faults": 0,
          "wins": 64
        },
        {
          "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-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": 46,
          "model": "claude-opus-4-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-a75e9d71efa4a6bc",
          "rated_matches": 106,
          "raw_elo_rating": 1490.8078638278364,
          "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": 41.629120841132384,
          "uncertainty": 4.586824452283178,
          "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": "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": "legacy_shared_thinking_budget",
          "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": 120,
          "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-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": 55,
          "model": "claude-opus-4-8",
          "point_rating_method": "sequential_elo",
          "public_id": "E-924d7e6ee41b562e",
          "rated_matches": 120,
          "raw_elo_rating": 1542.2837822150532,
          "reasoning": "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": 46.70493564691155,
          "uncertainty": 1.7045454545454586,
          "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": "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": 112,
          "raw_elo_rating": 1876.0974674925728,
          "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": 78.09020662768593,
          "uncertainty": 3.286043419179858,
          "unilateral_faults": 0,
          "wins": 94
        },
        {
          "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": "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": 110,
          "raw_elo_rating": 1960.9587096531482,
          "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": 86.06739228415002,
          "uncertainty": 3.707899787624953,
          "unilateral_faults": 0,
          "wins": 100
        },
        {
          "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-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": 1592.58297021455,
          "reasoning": "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": 51.19986121676889,
          "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": 1554.187571180924,
          "reasoning": "enabled",
          "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": 47.116586312570426,
          "uncertainty": 11.132129994845172,
          "unilateral_faults": 0,
          "wins": 46
        },
        {
          "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": 46,
          "model": "deepseek/deepseek-v4-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-06a41d0e11b18b77",
          "rated_matches": 76,
          "raw_elo_rating": 1376.1999302626996,
          "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": 30.160047415863634,
          "uncertainty": 13.230288229818967,
          "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": "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-2c1cbd253f3a9d69",
          "rated_matches": 78,
          "raw_elo_rating": 1315.440789501957,
          "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": 24.48052611809984,
          "uncertainty": 12.5043950463012,
          "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": 1239.8542944594315,
          "reasoning": "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": 17.8000252646134,
          "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": 1549.9264735902525,
          "reasoning": "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": 47.30683087113872,
          "uncertainty": 3.286043419179858,
          "unilateral_faults": 0,
          "wins": 58
        },
        {
          "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": "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": 56,
          "model": "google/gemini-3.5-flash-lite",
          "point_rating_method": "sequential_elo",
          "public_id": "E-3dd83d6fa9f8f758",
          "rated_matches": 74,
          "raw_elo_rating": 1260.8677419977996,
          "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": 19.218238123695905,
          "uncertainty": 13.985026918962571,
          "unilateral_faults": 0,
          "wins": 18
        },
        {
          "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": "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": 54,
          "model": "google/gemini-3.5-flash-lite",
          "point_rating_method": "sequential_elo",
          "public_id": "E-8826ab29e7591ece",
          "rated_matches": 74,
          "raw_elo_rating": 1330.739735653201,
          "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": 25.812619217550747,
          "uncertainty": 13.985026918962571,
          "unilateral_faults": 0,
          "wins": 20
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 72,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 36,
          "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": 3,
          "model": "google/gemini-3.6-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-5bcc61f900210bfa",
          "rated_matches": 72,
          "raw_elo_rating": 1944.9376572512983,
          "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": 83.72009823827334,
          "uncertainty": 14.770573598065289,
          "unilateral_faults": 0,
          "wins": 69
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 72,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 36,
          "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": 36,
          "model": "google/gemini-3.6-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-d95a1da824d70f6d",
          "rated_matches": 72,
          "raw_elo_rating": 1652.07513525259,
          "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": 56.0803104329967,
          "uncertainty": 14.770573598065289,
          "unilateral_faults": 0,
          "wins": 36
        },
        {
          "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": "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": 33,
          "model": "google/gemma-4-31b-it",
          "point_rating_method": "sequential_elo",
          "public_id": "E-fd1bc1e2e6ac48fb",
          "rated_matches": 78,
          "raw_elo_rating": 1535.4737363387264,
          "reasoning": "enabled",
          "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": 45.246802114196214,
          "uncertainty": 12.5043950463012,
          "unilateral_faults": 0,
          "wins": 45
        },
        {
          "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": 1602.5266986191143,
          "reasoning": "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": 52.1027343192657,
          "uncertainty": 5.516463908214657,
          "unilateral_faults": 0,
          "wins": 50
        },
        {
          "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": "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": 68,
          "model": "gpt-5.4",
          "point_rating_method": "sequential_elo",
          "public_id": "E-cafab3c275850d3b",
          "rated_matches": 118,
          "raw_elo_rating": 1475.0224962569089,
          "reasoning": "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": 40.32822843528254,
          "uncertainty": 2.084924851410568,
          "unilateral_faults": 0,
          "wins": 50
        },
        {
          "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-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-0791f6b66243ec1a",
          "rated_matches": 120,
          "raw_elo_rating": 1568.875101313137,
          "reasoning": "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": 49.214571951063434,
          "uncertainty": 1.7045454545454586,
          "unilateral_faults": 0,
          "wins": 72
        },
        {
          "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": 1805.1714752058563,
          "reasoning": "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": 71.03306818811886,
          "uncertainty": 8.09758473652126,
          "unilateral_faults": 0,
          "wins": 75
        },
        {
          "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": "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": 77,
          "model": "gpt-5.4-nano",
          "point_rating_method": "sequential_elo",
          "public_id": "E-a0d8c8fd6b01598c",
          "rated_matches": 114,
          "raw_elo_rating": 1292.1590187874883,
          "reasoning": "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": 23.010262983466863,
          "uncertainty": 2.875240412015687,
          "unilateral_faults": 0,
          "wins": 37
        },
        {
          "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": "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": 30,
          "model": "gpt-5.5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-ffa82d1e96e897ab",
          "rated_matches": 96,
          "raw_elo_rating": 1733.9891021907006,
          "reasoning": "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": 64.39657956468047,
          "uncertainty": 7.017308256680951,
          "unilateral_faults": 0,
          "wins": 66
        },
        {
          "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": 1599.0265614912312,
          "reasoning": "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": 52.00203493565957,
          "uncertainty": 2.4750163521024238,
          "unilateral_faults": 0,
          "wins": 57
        },
        {
          "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": 1672.1305254535307,
          "reasoning": "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": 58.59740424093167,
          "uncertainty": 6.501890762960602,
          "unilateral_faults": 0,
          "wins": 61
        },
        {
          "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": "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": 44,
          "model": "gpt-5.6-terra",
          "point_rating_method": "sequential_elo",
          "public_id": "E-9664e98d37ece097",
          "rated_matches": 108,
          "raw_elo_rating": 1604.4100113362138,
          "reasoning": "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": 52.384304794269354,
          "uncertainty": 4.1413142610575715,
          "unilateral_faults": 0,
          "wins": 64
        },
        {
          "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": "openrouter",
            "effective_request_value": "enabled",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "meituan/longcat-2.0",
            "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 22,
          "model": "meituan/longcat-2.0",
          "point_rating_method": "sequential_elo",
          "public_id": "E-73a7ad076eeaa6ae",
          "rated_matches": 52,
          "raw_elo_rating": 1516.8265772811042,
          "reasoning": "enabled",
          "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": 42.548735401808244,
          "uncertainty": 24.930281974344517,
          "unilateral_faults": 0,
          "wins": 30
        },
        {
          "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": "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-8b7eb63d4f53d846",
          "rated_matches": 52,
          "raw_elo_rating": 1280.9325986704027,
          "reasoning": "enabled",
          "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": 20.285526477550572,
          "uncertainty": 24.930281974344517,
          "unilateral_faults": 0,
          "wins": 13
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 68,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 34,
          "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": 66,
          "model": "minimax/minimax-m3",
          "point_rating_method": "sequential_elo",
          "public_id": "E-fb8ac45946e32e22",
          "rated_matches": 68,
          "raw_elo_rating": 1108.414675586985,
          "reasoning": "enabled",
          "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": 4.644440711956799,
          "uncertainty": 16.4429265428846,
          "unilateral_faults": 0,
          "wins": 2
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 64,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 32,
          "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": 24,
          "model": "moonshotai/kimi-k2.7-code",
          "point_rating_method": "sequential_elo",
          "public_id": "E-952fba19b28982d5",
          "rated_matches": 64,
          "raw_elo_rating": 1670.0314312667674,
          "reasoning": "enabled",
          "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": 57.51097387236131,
          "uncertainty": 18.26736729460423,
          "unilateral_faults": 0,
          "wins": 40
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 56,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 28,
          "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": 21,
          "model": "moonshotai/kimi-k3",
          "point_rating_method": "sequential_elo",
          "public_id": "E-895556dde47644ae",
          "rated_matches": 56,
          "raw_elo_rating": 1581.175060687989,
          "reasoning": "high",
          "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": 48.807076069542,
          "uncertainty": 22.47661785325219,
          "unilateral_faults": 0,
          "wins": 35
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 66,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 33,
          "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": 56,
          "model": "nex-agi/nex-n2-pro",
          "point_rating_method": "sequential_elo",
          "public_id": "E-5f76f577111bee8d",
          "rated_matches": 66,
          "raw_elo_rating": 1177.8086480503327,
          "reasoning": "enabled",
          "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": 11.12637437556477,
          "uncertainty": 17.33472217815261,
          "unilateral_faults": 0,
          "wins": 10
        },
        {
          "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": "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": 48,
          "model": "o3",
          "point_rating_method": "sequential_elo",
          "public_id": "E-343b92f3dda3dcb5",
          "rated_matches": 112,
          "raw_elo_rating": 1546.9217609319278,
          "reasoning": "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": 47.02325201056916,
          "uncertainty": 3.286043419179858,
          "unilateral_faults": 0,
          "wins": 64
        },
        {
          "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": "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": 114,
          "raw_elo_rating": 1455.3098804014994,
          "reasoning": "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": 38.408119849833696,
          "uncertainty": 2.875240412015687,
          "unilateral_faults": 0,
          "wins": 47
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 50,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 25,
          "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": 40,
          "model": "poolside/laguna-s-2.1",
          "point_rating_method": "sequential_elo",
          "public_id": "E-53ce0020411c86d4",
          "rated_matches": 50,
          "raw_elo_rating": 1267.1393490091898,
          "reasoning": "enabled",
          "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": 18.883047490292018,
          "uncertainty": 26.264004201400486,
          "unilateral_faults": 0,
          "wins": 10
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 58,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 29,
          "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": 36,
          "model": "poolside/laguna-s-2.1",
          "point_rating_method": "sequential_elo",
          "public_id": "E-62e15a037ee860c1",
          "rated_matches": 58,
          "raw_elo_rating": 1394.0878683267222,
          "reasoning": "enabled",
          "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": 31.235636471008934,
          "uncertainty": 21.344455490411935,
          "unilateral_faults": 0,
          "wins": 22
        },
        {
          "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": "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": 41,
          "model": "qwen/qwen3.7-max",
          "point_rating_method": "sequential_elo",
          "public_id": "E-435ec29661cdc285",
          "rated_matches": 82,
          "raw_elo_rating": 1569.2962092388195,
          "reasoning": "enabled",
          "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": 48.54250980423797,
          "uncertainty": 11.132129994845172,
          "unilateral_faults": 0,
          "wins": 41
        },
        {
          "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": "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": 43,
          "model": "qwen/qwen3.7-plus",
          "point_rating_method": "sequential_elo",
          "public_id": "E-6cc7454f585005c4",
          "rated_matches": 80,
          "raw_elo_rating": 1558.141803831932,
          "reasoning": "enabled",
          "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": 47.43893373716316,
          "uncertainty": 11.805555555555554,
          "unilateral_faults": 0,
          "wins": 37
        },
        {
          "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": "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-7b9b33921ba865f5",
          "rated_matches": 116,
          "raw_elo_rating": 1490.9069818743108,
          "reasoning": "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": 41.79792203718302,
          "uncertainty": 2.4750163521024238,
          "unilateral_faults": 0,
          "wins": 52
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 122,
          "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": 78,
          "model": "thinkingmachines/inkling",
          "point_rating_method": "sequential_elo",
          "public_id": "E-ae60ed096a69eeff",
          "rated_matches": 122,
          "raw_elo_rating": 1331.9093913458112,
          "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": 26.878231343301803,
          "uncertainty": 1.3334817333716131,
          "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": "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": 1662.7933410041032,
          "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": 58.02021794771947,
          "uncertainty": 2.4750163521024238,
          "unilateral_faults": 0,
          "wins": 70
        },
        {
          "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": "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": 30,
          "model": "x-ai/grok-build-0.1",
          "point_rating_method": "sequential_elo",
          "public_id": "E-4aac1b6621aeae38",
          "rated_matches": 74,
          "raw_elo_rating": 1582.6074425749334,
          "reasoning": "enabled",
          "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": 49.58339714709747,
          "uncertainty": 13.985026918962571,
          "unilateral_faults": 0,
          "wins": 44
        },
        {
          "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": "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": 48,
          "model": "xiaomi/mimo-v2.5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-ad48cf51fe7da3cc",
          "rated_matches": 70,
          "raw_elo_rating": 1309.2771310691762,
          "reasoning": "enabled",
          "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": 23.66591076906232,
          "uncertainty": 15.58908290969266,
          "unilateral_faults": 0,
          "wins": 22
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 58,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 29,
          "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": 48,
          "model": "xiaomi/mimo-v2.5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-faaa866ee28d6401",
          "rated_matches": 58,
          "raw_elo_rating": 1251.5086316908314,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "repaired",
          "score": 17.77928903823047,
          "uncertainty": 21.344455490411935,
          "unilateral_faults": 0,
          "wins": 10
        },
        {
          "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": "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": 52,
          "model": "xiaomi/mimo-v2.5-pro",
          "point_rating_method": "sequential_elo",
          "public_id": "E-9c228ad72a159b33",
          "rated_matches": 70,
          "raw_elo_rating": 1340.5127394994104,
          "reasoning": "enabled",
          "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": 26.613865949835468,
          "uncertainty": 15.58908290969266,
          "unilateral_faults": 0,
          "wins": 18
        },
        {
          "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": 40,
          "model": "z-ai/glm-5.2",
          "point_rating_method": "sequential_elo",
          "public_id": "E-3916ba303b2ff700",
          "rated_matches": 82,
          "raw_elo_rating": 1575.0888414631513,
          "reasoning": "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": 49.08920702046711,
          "uncertainty": 11.132129994845172,
          "unilateral_faults": 0,
          "wins": 42
        }
      ],
      "GB2-06": [
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 92,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 46,
          "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": 1783.3077264160918,
          "reasoning": "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": 84.02163040431354,
          "uncertainty": 8.09758473652126,
          "unilateral_faults": 0,
          "wins": 65
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 104,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 52,
          "draws": 9,
          "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": 42,
          "model": "claude-opus-4-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-1ff6d6f973c7157d",
          "rated_matches": 104,
          "raw_elo_rating": 1549.8531936911686,
          "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": 59.445585881637015,
          "uncertainty": 5.045003647426665,
          "unilateral_faults": 0,
          "wins": 53
        },
        {
          "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": "legacy_shared_thinking_budget",
          "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": 90,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 45,
          "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": 90,
          "raw_elo_rating": 1774.7289447776332,
          "reasoning": "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": 83.06075814643916,
          "uncertainty": 8.664241836095918,
          "unilateral_faults": 0,
          "wins": 67
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 116,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 58,
          "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": 51,
          "model": "claude-sonnet-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-01597b81edc004dd",
          "rated_matches": 116,
          "raw_elo_rating": 1466.154060432485,
          "reasoning": "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": 50.76005671360996,
          "uncertainty": 2.4750163521024238,
          "unilateral_faults": 0,
          "wins": 61
        },
        {
          "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": 1247.029922882203,
          "reasoning": "enabled",
          "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": 26.332638922125277,
          "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": 1404.8183545629643,
          "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": 43.44081870236101,
          "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": 1198.555065024979,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "repaired",
          "score": 21.497692280757313,
          "uncertainty": 11.805555555555554,
          "unilateral_faults": 0,
          "wins": 20
        },
        {
          "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-3.1-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": 80,
          "model": "google/gemini-3.1-flash-lite",
          "point_rating_method": "sequential_elo",
          "public_id": "E-a10101fbca309818",
          "rated_matches": 130,
          "raw_elo_rating": 1451.1115221856815,
          "reasoning": "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": 49.375926945379035,
          "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": 1843.3512911845396,
          "reasoning": "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": 90.25968655583348,
          "uncertainty": 9.855626741889738,
          "unilateral_faults": 0,
          "wins": 63
        },
        {
          "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": "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": 60,
          "model": "google/gemini-3.5-flash-lite",
          "point_rating_method": "sequential_elo",
          "public_id": "E-3d6c386b0f48e1c1",
          "rated_matches": 70,
          "raw_elo_rating": 1180.741110072107,
          "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": 19.280565801949013,
          "uncertainty": 15.58908290969266,
          "unilateral_faults": 0,
          "wins": 10
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 70,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 35,
          "draws": 2,
          "evaluated_setting_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": 53,
          "model": "google/gemini-3.5-flash-lite",
          "point_rating_method": "sequential_elo",
          "public_id": "E-892a28a528dad9c8",
          "rated_matches": 70,
          "raw_elo_rating": 1180.3935957061635,
          "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": 19.243595812367733,
          "uncertainty": 15.58908290969266,
          "unilateral_faults": 0,
          "wins": 15
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 66,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 33,
          "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": "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-33485e8cce3184c3",
          "rated_matches": 66,
          "raw_elo_rating": 1822.6642288553644,
          "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": 87.42238761314094,
          "uncertainty": 17.33472217815261,
          "unilateral_faults": 0,
          "wins": 53
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 66,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 33,
          "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-3.6-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": 4,
          "model": "google/gemini-3.6-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-bdf020e4fa85b365",
          "rated_matches": 66,
          "raw_elo_rating": 1903.1203221826072,
          "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": 95.98163357117124,
          "uncertainty": 17.33472217815261,
          "unilateral_faults": 0,
          "wins": 58
        },
        {
          "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": "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": 53,
          "model": "google/gemma-4-31b-it",
          "point_rating_method": "sequential_elo",
          "public_id": "E-41987f96551bf9d3",
          "rated_matches": 70,
          "raw_elo_rating": 1304.264016556007,
          "reasoning": "enabled",
          "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": 32.421434247378265,
          "uncertainty": 15.58908290969266,
          "unilateral_faults": 0,
          "wins": 17
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 100,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 50,
          "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": 40,
          "model": "gpt-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-816d262cd933cdb9",
          "rated_matches": 100,
          "raw_elo_rating": 1589.115508396417,
          "reasoning": "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": 63.54103500269817,
          "uncertainty": 6.001859510499461,
          "unilateral_faults": 0,
          "wins": 53
        },
        {
          "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": 1892.891192538813,
          "reasoning": "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": 95.42130277416098,
          "uncertainty": 11.132129994845172,
          "unilateral_faults": 0,
          "wins": 68
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 106,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 53,
          "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": 42,
          "model": "gpt-5.4-mini",
          "point_rating_method": "sequential_elo",
          "public_id": "E-3ccfe46cbdc271eb",
          "rated_matches": 106,
          "raw_elo_rating": 1574.0883296357088,
          "reasoning": "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": 62.06281243846746,
          "uncertainty": 4.586824452283178,
          "unilateral_faults": 0,
          "wins": 52
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 108,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 54,
          "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": 108,
          "raw_elo_rating": 1654.2541365710636,
          "reasoning": "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": 70.62909269797777,
          "uncertainty": 4.1413142610575715,
          "unilateral_faults": 0,
          "wins": 58
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 102,
          "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": 102,
          "raw_elo_rating": 1563.1232477876315,
          "reasoning": "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": 60.8171834432279,
          "uncertainty": 5.516463908214657,
          "unilateral_faults": 0,
          "wins": 60
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 120,
          "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": 72,
          "model": "gpt-5.5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-1ea2c2c23d752166",
          "rated_matches": 120,
          "raw_elo_rating": 1493.0993164354797,
          "reasoning": "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": 53.69217513632242,
          "uncertainty": 1.7045454545454586,
          "unilateral_faults": 0,
          "wins": 47
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 106,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 53,
          "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": 106,
          "raw_elo_rating": 1655.1398493340357,
          "reasoning": "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": 70.68540227201106,
          "uncertainty": 4.586824452283178,
          "unilateral_faults": 0,
          "wins": 64
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 92,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 46,
          "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": 1792.977450720159,
          "reasoning": "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": 85.05033494665588,
          "uncertainty": 8.09758473652126,
          "unilateral_faults": 0,
          "wins": 64
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 100,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 50,
          "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": 41,
          "model": "gpt-5.6-terra",
          "point_rating_method": "sequential_elo",
          "public_id": "E-a3722334e358f0fe",
          "rated_matches": 100,
          "raw_elo_rating": 1507.497978964082,
          "reasoning": "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": 54.85823075496087,
          "uncertainty": 6.001859510499461,
          "unilateral_faults": 0,
          "wins": 47
        },
        {
          "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": 1302.9988054239868,
          "reasoning": "enabled",
          "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": 31.491832194325372,
          "uncertainty": 24.930281974344517,
          "unilateral_faults": 0,
          "wins": 15
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 48,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 24,
          "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": "meituan/longcat-2.0",
            "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 28,
          "model": "meituan/longcat-2.0",
          "point_rating_method": "sequential_elo",
          "public_id": "E-0e252768ba2388c4",
          "rated_matches": 48,
          "raw_elo_rating": 1345.5858403280065,
          "reasoning": "enabled",
          "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": 35.78851456788528,
          "uncertainty": 27.678571428571434,
          "unilateral_faults": 0,
          "wins": 17
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 50,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 25,
          "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": "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": 25,
          "model": "meituan/longcat-2.0",
          "point_rating_method": "sequential_elo",
          "public_id": "E-a9bdeb6a9326ac2d",
          "rated_matches": 50,
          "raw_elo_rating": 1411.4177641966762,
          "reasoning": "enabled",
          "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": 42.91237191214209,
          "uncertainty": 26.264004201400486,
          "unilateral_faults": 0,
          "wins": 22
        },
        {
          "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": "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": 54,
          "model": "minimax/minimax-m3",
          "point_rating_method": "sequential_elo",
          "public_id": "E-ef8c1a9fa3580f83",
          "rated_matches": 70,
          "raw_elo_rating": 1284.202251048526,
          "reasoning": "enabled",
          "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": 30.287182157453405,
          "uncertainty": 15.58908290969266,
          "unilateral_faults": 0,
          "wins": 16
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 66,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 33,
          "draws": 4,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "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": 25,
          "model": "moonshotai/kimi-k3",
          "point_rating_method": "sequential_elo",
          "public_id": "E-1640f1438f9390d7",
          "rated_matches": 66,
          "raw_elo_rating": 1534.9056491032766,
          "reasoning": "high",
          "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": 56.80946124827584,
          "uncertainty": 17.33472217815261,
          "unilateral_faults": 0,
          "wins": 37
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 70,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 35,
          "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": "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": 57,
          "model": "nex-agi/nex-n2-pro",
          "point_rating_method": "sequential_elo",
          "public_id": "E-209380b737b62580",
          "rated_matches": 70,
          "raw_elo_rating": 1191.967079496774,
          "reasoning": "enabled",
          "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": 20.47483002047425,
          "uncertainty": 15.58908290969266,
          "unilateral_faults": 0,
          "wins": 8
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 96,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 48,
          "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": 96,
          "raw_elo_rating": 1613.9350142082228,
          "reasoning": "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": 66.09501277916272,
          "uncertainty": 7.017308256680951,
          "unilateral_faults": 0,
          "wins": 51
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 102,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 51,
          "draws": 10,
          "evaluated_setting_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-69e964db7b91b1bb",
          "rated_matches": 102,
          "raw_elo_rating": 1607.5937026330773,
          "reasoning": "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": 65.54813103397758,
          "uncertainty": 5.516463908214657,
          "unilateral_faults": 0,
          "wins": 50
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 121,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 61,
          "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": 1384.137730967665,
          "reasoning": "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": 42.11628633456594,
          "uncertainty": 1.5178730212592662,
          "unilateral_faults": 0,
          "wins": 42
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 48,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 24,
          "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": "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": 29,
          "model": "poolside/laguna-s-2.1",
          "point_rating_method": "sequential_elo",
          "public_id": "E-b582570ce841ee30",
          "rated_matches": 48,
          "raw_elo_rating": 1331.9790233058707,
          "reasoning": "enabled",
          "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": 34.34096611279594,
          "uncertainty": 27.678571428571434,
          "unilateral_faults": 0,
          "wins": 18
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 70,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 35,
          "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-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": 25,
          "model": "qwen/qwen3.7-max",
          "point_rating_method": "sequential_elo",
          "public_id": "E-8283efe6f68a787e",
          "rated_matches": 70,
          "raw_elo_rating": 1615.2240279036346,
          "reasoning": "enabled",
          "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": 65.50262313148998,
          "uncertainty": 15.58908290969266,
          "unilateral_faults": 0,
          "wins": 40
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 62,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 31,
          "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": "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": 12,
          "model": "qwen/qwen3.7-plus",
          "point_rating_method": "sequential_elo",
          "public_id": "E-b6dd11ebe2b80c7b",
          "rated_matches": 62,
          "raw_elo_rating": 1768.9651446619,
          "reasoning": "enabled",
          "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": 81.54716086048992,
          "uncertainty": 19.244078834871203,
          "unilateral_faults": 0,
          "wins": 47
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 110,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 55,
          "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": 76,
          "model": "stepfun/step-3.7-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-6526762dce98da7c",
          "rated_matches": 110,
          "raw_elo_rating": 1299.6101532628288,
          "reasoning": "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": 32.937512179985525,
          "uncertainty": 3.707899787624953,
          "unilateral_faults": 0,
          "wins": 33
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 120,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 60,
          "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": 61,
          "model": "x-ai/grok-4.5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-3baaff3521870bef",
          "rated_matches": 120,
          "raw_elo_rating": 1442.0865376108627,
          "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": 48.2652285508529,
          "uncertainty": 1.7045454545454586,
          "unilateral_faults": 0,
          "wins": 51
        },
        {
          "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": "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": 48,
          "model": "x-ai/grok-build-0.1",
          "point_rating_method": "sequential_elo",
          "public_id": "E-133675db0ee21fd5",
          "rated_matches": 70,
          "raw_elo_rating": 1347.5318338568136,
          "reasoning": "enabled",
          "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": 37.024440371953844,
          "uncertainty": 15.58908290969266,
          "unilateral_faults": 0,
          "wins": 22
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 70,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 35,
          "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": "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": 52,
          "model": "xiaomi/mimo-v2.5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-7b4c450b6850f156",
          "rated_matches": 70,
          "raw_elo_rating": 1291.0631630919836,
          "reasoning": "enabled",
          "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": 31.01707384430817,
          "uncertainty": 15.58908290969266,
          "unilateral_faults": 0,
          "wins": 14
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 62,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 31,
          "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": 17,
          "model": "xiaomi/mimo-v2.5-pro",
          "point_rating_method": "sequential_elo",
          "public_id": "E-530f82d65699c577",
          "rated_matches": 62,
          "raw_elo_rating": 1690.6528962825803,
          "reasoning": "enabled",
          "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": 73.21598583464518,
          "uncertainty": 19.244078834871203,
          "unilateral_faults": 0,
          "wins": 45
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 68,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 34,
          "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": "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": 68,
          "raw_elo_rating": 1655.2045242420968,
          "reasoning": "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": 69.68324241888193,
          "uncertainty": 16.4429265428846,
          "unilateral_faults": 0,
          "wins": 35
        }
      ],
      "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": 1762.4042745072609,
          "reasoning": "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": 71.79611330973476,
          "uncertainty": 8.664241836095918,
          "unilateral_faults": 0,
          "wins": 70
        },
        {
          "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": "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": 55,
          "model": "claude-opus-4-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-e7848fdc8b4ffd95",
          "rated_matches": 104,
          "raw_elo_rating": 1484.9594600967189,
          "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": 44.455587919211716,
          "uncertainty": 5.045003647426665,
          "unilateral_faults": 0,
          "wins": 49
        },
        {
          "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": "legacy_shared_thinking_budget",
          "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": 100,
          "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-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": 100,
          "raw_elo_rating": 1667.8017327798075,
          "reasoning": "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": 62.58738719657233,
          "uncertainty": 6.001859510499461,
          "unilateral_faults": 0,
          "wins": 66
        },
        {
          "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": "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": 84,
          "raw_elo_rating": 1979.410637944388,
          "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": 93.26144984700437,
          "uncertainty": 10.482614454664043,
          "unilateral_faults": 0,
          "wins": 79
        },
        {
          "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": 28,
          "model": "claude-opus-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-de5e72176c4f0dc9",
          "rated_matches": 104,
          "raw_elo_rating": 1815.7391470039968,
          "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": 77.39570595487102,
          "uncertainty": 5.045003647426665,
          "unilateral_faults": 0,
          "wins": 76
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 122,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 61,
          "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": 50,
          "model": "claude-sonnet-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-9e40526fba9fa8b9",
          "rated_matches": 122,
          "raw_elo_rating": 1548.1539016254237,
          "reasoning": "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": 51.044380476224916,
          "uncertainty": 1.3334817333716131,
          "unilateral_faults": 0,
          "wins": 72
        },
        {
          "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": 1399.0487098290237,
          "reasoning": "enabled",
          "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": 35.248221907515756,
          "uncertainty": 13.230288229818967,
          "unilateral_faults": 0,
          "wins": 29
        },
        {
          "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": "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": 47,
          "model": "deepseek/deepseek-v4-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-8f2f6c973751f183",
          "rated_matches": 74,
          "raw_elo_rating": 1380.9199425547763,
          "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": 33.38277277782705,
          "uncertainty": 13.985026918962571,
          "unilateral_faults": 0,
          "wins": 27
        },
        {
          "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": "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": 39,
          "model": "deepseek/deepseek-v4-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-edc2d085c4253ed3",
          "rated_matches": 74,
          "raw_elo_rating": 1530.8826673809547,
          "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": 48.316549101607485,
          "uncertainty": 13.985026918962571,
          "unilateral_faults": 0,
          "wins": 35
        },
        {
          "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": "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": 80,
          "model": "google/gemini-3.1-flash-lite",
          "point_rating_method": "sequential_elo",
          "public_id": "E-1b3c52da51dfbdd4",
          "rated_matches": 92,
          "raw_elo_rating": 1052.903259206907,
          "reasoning": "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": 1.18683615794815,
          "uncertainty": 8.09758473652126,
          "unilateral_faults": 0,
          "wins": 12
        },
        {
          "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": "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": 51,
          "model": "google/gemini-3.5-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-5447c508e2b0ab6c",
          "rated_matches": 106,
          "raw_elo_rating": 1583.0678904088375,
          "reasoning": "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": 54.26204637051112,
          "uncertainty": 4.586824452283178,
          "unilateral_faults": 0,
          "wins": 55
        },
        {
          "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": "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": 48,
          "model": "google/gemini-3.5-flash-lite",
          "point_rating_method": "sequential_elo",
          "public_id": "E-f74134262b66367b",
          "rated_matches": 70,
          "raw_elo_rating": 1257.5590178307139,
          "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": 20.97030061327731,
          "uncertainty": 15.58908290969266,
          "unilateral_faults": 0,
          "wins": 22
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 68,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 34,
          "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": 32,
          "model": "google/gemini-3.6-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-1f7519ff2c4a840c",
          "rated_matches": 68,
          "raw_elo_rating": 1638.7684416591005,
          "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": 58.864353196612875,
          "uncertainty": 16.4429265428846,
          "unilateral_faults": 0,
          "wins": 36
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 128,
          "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": 53,
          "model": "google/gemini-3.6-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-65c6c8e09fe2c210",
          "rated_matches": 128,
          "raw_elo_rating": 1490.1292333854794,
          "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": 45.35061632230381,
          "uncertainty": 0.27254531628119416,
          "unilateral_faults": 0,
          "wins": 75
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 66,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 33,
          "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": 43,
          "model": "google/gemma-4-31b-it",
          "point_rating_method": "sequential_elo",
          "public_id": "E-f417d302c870dfa6",
          "rated_matches": 66,
          "raw_elo_rating": 1349.313649651218,
          "reasoning": "enabled",
          "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": 29.96845639325902,
          "uncertainty": 17.33472217815261,
          "unilateral_faults": 0,
          "wins": 23
        },
        {
          "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",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_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",
          "point_rating_method": "sequential_elo",
          "public_id": "E-4d8b4cfcff519db6",
          "rated_matches": 98,
          "raw_elo_rating": 1638.5757431946397,
          "reasoning": "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": 59.63713222006284,
          "uncertainty": 6.501890762960602,
          "unilateral_faults": 0,
          "wins": 59
        },
        {
          "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": "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": 100,
          "raw_elo_rating": 1645.147005295843,
          "reasoning": "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": 60.331355683982295,
          "uncertainty": 6.001859510499461,
          "unilateral_faults": 0,
          "wins": 65
        },
        {
          "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": "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": 106,
          "raw_elo_rating": 1545.2161928372725,
          "reasoning": "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": 50.492651104691994,
          "uncertainty": 4.586824452283178,
          "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": "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": 1200.2033445884742,
          "reasoning": "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": 15.899168625252624,
          "uncertainty": 7.54891760425771,
          "unilateral_faults": 0,
          "wins": 16
        },
        {
          "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-5.4-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": 34,
          "model": "gpt-5.4-nano",
          "point_rating_method": "sequential_elo",
          "public_id": "E-ce04fd14b6f43868",
          "rated_matches": 98,
          "raw_elo_rating": 1643.5092706977405,
          "reasoning": "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": 60.12842894932622,
          "uncertainty": 6.501890762960602,
          "unilateral_faults": 0,
          "wins": 64
        },
        {
          "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": "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": 1732.0611905000076,
          "reasoning": "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": 68.86330432028504,
          "uncertainty": 7.54891760425771,
          "unilateral_faults": 0,
          "wins": 62
        },
        {
          "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": "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": 62,
          "model": "gpt-5.6-luna",
          "point_rating_method": "sequential_elo",
          "public_id": "E-45c76cf9faaba10a",
          "rated_matches": 112,
          "raw_elo_rating": 1521.5171741625923,
          "reasoning": "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": 48.23625448361621,
          "uncertainty": 3.286043419179858,
          "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": "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": 1641.3171931289405,
          "reasoning": "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": 59.9101347289806,
          "uncertainty": 6.501890762960602,
          "unilateral_faults": 0,
          "wins": 60
        },
        {
          "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": "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": 1401.2822756940366,
          "reasoning": "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": 36.2955991645047,
          "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": 1496.9801801957265,
          "reasoning": "enabled",
          "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": 44.0684577587389,
          "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": 1429.9790809110914,
          "reasoning": "enabled",
          "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": 37.39627017796564,
          "uncertainty": 24.930281974344517,
          "unilateral_faults": 0,
          "wins": 19
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 50,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 25,
          "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
            "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": "meituan/longcat-2.0",
          "point_rating_method": "sequential_elo",
          "public_id": "E-28ec7bff448d69bb",
          "rated_matches": 50,
          "raw_elo_rating": 1710.7882394632145,
          "reasoning": "enabled",
          "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": 65.25390720606802,
          "uncertainty": 26.264004201400486,
          "unilateral_faults": 0,
          "wins": 34
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 44,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 22,
          "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": 33,
          "model": "meituan/longcat-2.0",
          "point_rating_method": "sequential_elo",
          "public_id": "E-fe21773d3155f05f",
          "rated_matches": 44,
          "raw_elo_rating": 1234.8618172648503,
          "reasoning": "enabled",
          "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": 17.499384638849104,
          "uncertainty": 30.785599249992988,
          "unilateral_faults": 0,
          "wins": 11
        },
        {
          "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": "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": 34,
          "model": "minimax/minimax-m3",
          "point_rating_method": "sequential_elo",
          "public_id": "E-4547f4cedca403f9",
          "rated_matches": 74,
          "raw_elo_rating": 1558.812989789706,
          "reasoning": "enabled",
          "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": 51.0979415308717,
          "uncertainty": 13.985026918962571,
          "unilateral_faults": 0,
          "wins": 40
        },
        {
          "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": "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": 32,
          "model": "moonshotai/kimi-k2.7-code",
          "point_rating_method": "sequential_elo",
          "public_id": "E-d35e87ebfc251f60",
          "rated_matches": 76,
          "raw_elo_rating": 1583.9094538021247,
          "reasoning": "enabled",
          "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": 53.65725658424505,
          "uncertainty": 13.230288229818967,
          "unilateral_faults": 0,
          "wins": 44
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 44,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 22,
          "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": 29,
          "model": "moonshotai/kimi-k3",
          "point_rating_method": "sequential_elo",
          "public_id": "E-55ef4536a723bcf7",
          "rated_matches": 44,
          "raw_elo_rating": 1385.765880772664,
          "reasoning": "high",
          "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": 32.5269025329615,
          "uncertainty": 30.785599249992988,
          "unilateral_faults": 0,
          "wins": 15
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 66,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 33,
          "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": 43,
          "model": "nex-agi/nex-n2-pro",
          "point_rating_method": "sequential_elo",
          "public_id": "E-d1f432cda667f27f",
          "rated_matches": 66,
          "raw_elo_rating": 1363.3468730726593,
          "reasoning": "enabled",
          "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": 31.36593046503488,
          "uncertainty": 17.33472217815261,
          "unilateral_faults": 0,
          "wins": 23
        },
        {
          "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": "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": 1165.7290719890677,
          "reasoning": "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": 12.422397885640807,
          "uncertainty": 8.09758473652126,
          "unilateral_faults": 0,
          "wins": 20
        },
        {
          "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": "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": 102,
          "raw_elo_rating": 1624.3448206991122,
          "reasoning": "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": 58.2984762422112,
          "uncertainty": 5.516463908214657,
          "unilateral_faults": 0,
          "wins": 60
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 58,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 29,
          "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": 8,
          "model": "qwen/qwen3.7-max",
          "point_rating_method": "sequential_elo",
          "public_id": "E-59c7745eb1e91d63",
          "rated_matches": 58,
          "raw_elo_rating": 1774.854267128815,
          "reasoning": "enabled",
          "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": 72.02573454075652,
          "uncertainty": 21.344455490411935,
          "unilateral_faults": 0,
          "wins": 50
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 68,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 34,
          "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": 40,
          "model": "qwen/qwen3.7-plus",
          "point_rating_method": "sequential_elo",
          "public_id": "E-9d091700cb41ece2",
          "rated_matches": 68,
          "raw_elo_rating": 1401.450531065138,
          "reasoning": "enabled",
          "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": 35.231463099790034,
          "uncertainty": 16.4429265428846,
          "unilateral_faults": 0,
          "wins": 28
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 68,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 34,
          "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": 58,
          "model": "thinkingmachines/inkling",
          "point_rating_method": "sequential_elo",
          "public_id": "E-b9ceec0ad4a1b9a4",
          "rated_matches": 68,
          "raw_elo_rating": 1196.149393725581,
          "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": 14.786907510390217,
          "uncertainty": 16.4429265428846,
          "unilateral_faults": 0,
          "wins": 10
        },
        {
          "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": 1630.4735516007104,
          "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": 59.08648524326837,
          "uncertainty": 3.286043419179858,
          "unilateral_faults": 0,
          "wins": 65
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 64,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 32,
          "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": 55,
          "model": "x-ai/grok-build-0.1",
          "point_rating_method": "sequential_elo",
          "public_id": "E-37ae0129627ee16f",
          "rated_matches": 64,
          "raw_elo_rating": 1198.4872693708057,
          "reasoning": "enabled",
          "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": 14.874373778371579,
          "uncertainty": 18.26736729460423,
          "unilateral_faults": 0,
          "wins": 9
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 56,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 28,
          "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": 29,
          "model": "xiaomi/mimo-v2.5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-345a5b25cbac7f3b",
          "rated_matches": 56,
          "raw_elo_rating": 1512.3181251054739,
          "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": 45.79133533231307,
          "uncertainty": 22.47661785325219,
          "unilateral_faults": 0,
          "wins": 27
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 66,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 33,
          "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": 43,
          "model": "xiaomi/mimo-v2.5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-fa1a93f7e4d57000",
          "rated_matches": 66,
          "raw_elo_rating": 1368.7633346415093,
          "reasoning": "enabled",
          "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": 31.905319340699265,
          "uncertainty": 17.33472217815261,
          "unilateral_faults": 0,
          "wins": 23
        },
        {
          "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": "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": 39,
          "model": "xiaomi/mimo-v2.5-pro",
          "point_rating_method": "sequential_elo",
          "public_id": "E-3b160130ae038271",
          "rated_matches": 78,
          "raw_elo_rating": 1568.0220467900822,
          "reasoning": "enabled",
          "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": 52.13296631946379,
          "uncertainty": 12.5043950463012,
          "unilateral_faults": 0,
          "wins": 39
        },
        {
          "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": "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": 32,
          "model": "z-ai/glm-5.2",
          "point_rating_method": "sequential_elo",
          "public_id": "E-ecd98326faa92bf4",
          "rated_matches": 78,
          "raw_elo_rating": 1545.2260932564172,
          "reasoning": "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": 49.862871057100186,
          "uncertainty": 12.5043950463012,
          "unilateral_faults": 0,
          "wins": 46
        }
      ],
      "GB2-08": [
        {
          "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": "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": 1814.5336004592846,
          "reasoning": "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": 72.22544650832927,
          "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": "legacy_shared_thinking_budget",
          "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": 84,
          "capped_draws": 1,
          "coverage_status": "rated",
          "distinct_rated_opponents": 42,
          "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-4-5",
            "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": 17,
          "model": "claude-opus-4-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-72233463ddce5549",
          "rated_matches": 84,
          "raw_elo_rating": 1789.2666943887314,
          "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": 69.00313139343699,
          "uncertainty": 10.482614454664043,
          "unilateral_faults": 0,
          "wins": 66
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 108,
          "capped_draws": 82,
          "coverage_status": "rated",
          "distinct_rated_opponents": 54,
          "draws": 82,
          "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": 108,
          "raw_elo_rating": 1422.9709089457906,
          "reasoning": "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": 26.170508876258452,
          "uncertainty": 4.1413142610575715,
          "unilateral_faults": 0,
          "wins": 5
        },
        {
          "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": "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": 100,
          "raw_elo_rating": 1846.6915020635672,
          "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": 76.23742971057715,
          "uncertainty": 6.001859510499461,
          "unilateral_faults": 0,
          "wins": 80
        },
        {
          "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": 8,
          "model": "claude-opus-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-e73b6fb78880341d",
          "rated_matches": 102,
          "raw_elo_rating": 1957.514655189079,
          "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": 89.4245253722117,
          "uncertainty": 5.516463908214657,
          "unilateral_faults": 0,
          "wins": 94
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 110,
          "capped_draws": 83,
          "coverage_status": "rated",
          "distinct_rated_opponents": 55,
          "draws": 83,
          "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": 110,
          "raw_elo_rating": 1426.2683033126514,
          "reasoning": "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": 26.602617521323882,
          "uncertainty": 3.707899787624953,
          "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": 1392.708579434299,
          "reasoning": "enabled",
          "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": 21.41515165958451,
          "uncertainty": 16.4429265428846,
          "unilateral_faults": 0,
          "wins": 0
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 78,
          "capped_draws": 69,
          "coverage_status": "rated",
          "distinct_rated_opponents": 39,
          "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": "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": 78,
          "raw_elo_rating": 1444.6969290589077,
          "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": 27.953376319747385,
          "uncertainty": 12.5043950463012,
          "unilateral_faults": 0,
          "wins": 2
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 82,
          "capped_draws": 71,
          "coverage_status": "rated",
          "distinct_rated_opponents": 41,
          "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": "2026-07-01T00:15:48Z",
          "losses": 9,
          "model": "deepseek/deepseek-v4-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-d28ef17ff6995c62",
          "rated_matches": 82,
          "raw_elo_rating": 1410.6372546204118,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "repaired",
          "score": 24.04486549659256,
          "uncertainty": 11.132129994845172,
          "unilateral_faults": 0,
          "wins": 2
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 130,
          "capped_draws": 40,
          "coverage_status": "rated",
          "distinct_rated_opponents": 65,
          "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": 130,
          "raw_elo_rating": 1436.5502098452275,
          "reasoning": "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": 28.179696020170926,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 39
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 88,
          "capped_draws": 67,
          "coverage_status": "rated",
          "distinct_rated_opponents": 44,
          "draws": 67,
          "evaluated_setting_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": 21,
          "model": "google/gemini-3.5-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-bd0bbefbbd252fc5",
          "rated_matches": 88,
          "raw_elo_rating": 1368.2923757001072,
          "reasoning": "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": 19.20229853735902,
          "uncertainty": 9.249894000318006,
          "unilateral_faults": 0,
          "wins": 0
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 76,
          "capped_draws": 62,
          "coverage_status": "rated",
          "distinct_rated_opponents": 38,
          "draws": 62,
          "evaluated_setting_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": 11,
          "model": "google/gemini-3.5-flash-lite",
          "point_rating_method": "sequential_elo",
          "public_id": "E-2f2aa5b1beafd6e6",
          "rated_matches": 76,
          "raw_elo_rating": 1431.6257184265396,
          "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": 26.334575273965037,
          "uncertainty": 13.230288229818967,
          "unilateral_faults": 0,
          "wins": 3
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 68,
          "capped_draws": 54,
          "coverage_status": "rated",
          "distinct_rated_opponents": 34,
          "draws": 54,
          "evaluated_setting_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": 12,
          "model": "google/gemini-3.5-flash-lite",
          "point_rating_method": "sequential_elo",
          "public_id": "E-9b50de854a87d3c6",
          "rated_matches": 68,
          "raw_elo_rating": 1427.9398227851348,
          "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": 25.59275832179461,
          "uncertainty": 16.4429265428846,
          "unilateral_faults": 0,
          "wins": 2
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 56,
          "capped_draws": 9,
          "coverage_status": "rated",
          "distinct_rated_opponents": 28,
          "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": "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": 17,
          "model": "google/gemini-3.6-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-ab7ee826f8050f04",
          "rated_matches": 56,
          "raw_elo_rating": 1654.1866708150255,
          "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": 51.848011910482846,
          "uncertainty": 22.47661785325219,
          "unilateral_faults": 0,
          "wins": 30
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 88,
          "capped_draws": 54,
          "coverage_status": "rated",
          "distinct_rated_opponents": 44,
          "draws": 54,
          "evaluated_setting_identity": {
            "canonical_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": 88,
          "raw_elo_rating": 1387.3551553183834,
          "reasoning": "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": 21.462701167505323,
          "uncertainty": 9.249894000318006,
          "unilateral_faults": 0,
          "wins": 8
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 100,
          "capped_draws": 38,
          "coverage_status": "rated",
          "distinct_rated_opponents": 50,
          "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": 31,
          "model": "gpt-5.4",
          "point_rating_method": "sequential_elo",
          "public_id": "E-b13a2be40d59c1ea",
          "rated_matches": 100,
          "raw_elo_rating": 1459.2219261759235,
          "reasoning": "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": 30.292543079332418,
          "uncertainty": 6.001859510499461,
          "unilateral_faults": 0,
          "wins": 31
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 114,
          "capped_draws": 41,
          "coverage_status": "rated",
          "distinct_rated_opponents": 57,
          "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": 1436.6611574632266,
          "reasoning": "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": 27.91395572652641,
          "uncertainty": 2.875240412015687,
          "unilateral_faults": 0,
          "wins": 35
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 94,
          "capped_draws": 52,
          "coverage_status": "rated",
          "distinct_rated_opponents": 47,
          "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": 1367.8675099857733,
          "reasoning": "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": 19.313276352756375,
          "uncertainty": 7.54891760425771,
          "unilateral_faults": 0,
          "wins": 5
        },
        {
          "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": "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": 1853.1383592528794,
          "reasoning": "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": 76.85512103552502,
          "uncertainty": 7.54891760425771,
          "unilateral_faults": 0,
          "wins": 72
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 112,
          "capped_draws": 50,
          "coverage_status": "rated",
          "distinct_rated_opponents": 56,
          "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": 1605.807541988619,
          "reasoning": "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": 47.93181649730258,
          "uncertainty": 3.286043419179858,
          "unilateral_faults": 0,
          "wins": 38
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 112,
          "capped_draws": 87,
          "coverage_status": "rated",
          "distinct_rated_opponents": 56,
          "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": 18,
          "model": "gpt-5.6-luna",
          "point_rating_method": "sequential_elo",
          "public_id": "E-e6198d88365e0492",
          "rated_matches": 112,
          "raw_elo_rating": 1429.4023399340574,
          "reasoning": "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": 27.014259316222454,
          "uncertainty": 3.286043419179858,
          "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": 1778.443049602078,
          "reasoning": "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": 67.83663626822397,
          "uncertainty": 9.249894000318006,
          "unilateral_faults": 0,
          "wins": 64
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 108,
          "capped_draws": 53,
          "coverage_status": "rated",
          "distinct_rated_opponents": 54,
          "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": 1485.5625871021477,
          "reasoning": "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": 33.5924272304032,
          "uncertainty": 4.1413142610575715,
          "unilateral_faults": 0,
          "wins": 21
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 42,
          "capped_draws": 17,
          "coverage_status": "rated",
          "distinct_rated_opponents": 21,
          "draws": 17,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "enabled",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "meituan/longcat-2.0",
            "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 24,
          "model": "meituan/longcat-2.0",
          "point_rating_method": "sequential_elo",
          "public_id": "E-d724da56cbc06da7",
          "rated_matches": 42,
          "raw_elo_rating": 1315.9608699542914,
          "reasoning": "enabled",
          "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": 10.791528209491693,
          "uncertainty": 32.49928516630233,
          "unilateral_faults": 0,
          "wins": 1
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 42,
          "capped_draws": 15,
          "coverage_status": "rated",
          "distinct_rated_opponents": 21,
          "draws": 15,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "enabled",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "meituan/longcat-2.0",
            "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 10,
          "model": "meituan/longcat-2.0",
          "point_rating_method": "sequential_elo",
          "public_id": "E-ef389910f6cc07cc",
          "rated_matches": 42,
          "raw_elo_rating": 1585.4966463069525,
          "reasoning": "enabled",
          "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": 42.75220708142079,
          "uncertainty": 32.49928516630233,
          "unilateral_faults": 0,
          "wins": 17
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 70,
          "capped_draws": 47,
          "coverage_status": "rated",
          "distinct_rated_opponents": 35,
          "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": "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": 16,
          "model": "minimax/minimax-m3",
          "point_rating_method": "sequential_elo",
          "public_id": "E-d169e7b29be70652",
          "rated_matches": 70,
          "raw_elo_rating": 1434.24782351636,
          "reasoning": "enabled",
          "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": 26.421737414855947,
          "uncertainty": 15.58908290969266,
          "unilateral_faults": 0,
          "wins": 7
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 60,
          "capped_draws": 4,
          "coverage_status": "rated",
          "distinct_rated_opponents": 30,
          "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": 11,
          "model": "moonshotai/kimi-k2.7-code",
          "point_rating_method": "sequential_elo",
          "public_id": "E-251b5d53a5f89562",
          "rated_matches": 60,
          "raw_elo_rating": 1723.2474480429453,
          "reasoning": "enabled",
          "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": 60.246485930241015,
          "uncertainty": 20.268439966447993,
          "unilateral_faults": 0,
          "wins": 45
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 62,
          "capped_draws": 43,
          "coverage_status": "rated",
          "distinct_rated_opponents": 31,
          "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": "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-151c4ee6a2d1838e",
          "rated_matches": 62,
          "raw_elo_rating": 1413.2261671604745,
          "reasoning": "high",
          "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": 23.582339471707066,
          "uncertainty": 19.244078834871203,
          "unilateral_faults": 0,
          "wins": 2
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 62,
          "capped_draws": 9,
          "coverage_status": "rated",
          "distinct_rated_opponents": 31,
          "draws": 9,
          "evaluated_setting_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": 49,
          "model": "nex-agi/nex-n2-pro",
          "point_rating_method": "sequential_elo",
          "public_id": "E-92332f4d765b2297",
          "rated_matches": 62,
          "raw_elo_rating": 1214.3479079348465,
          "reasoning": "enabled",
          "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": 19.244078834871203,
          "unilateral_faults": 0,
          "wins": 4
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 108,
          "capped_draws": 72,
          "coverage_status": "rated",
          "distinct_rated_opponents": 54,
          "draws": 72,
          "evaluated_setting_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": 108,
          "raw_elo_rating": 1440.809420939187,
          "reasoning": "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": 28.28574181894595,
          "uncertainty": 4.1413142610575715,
          "unilateral_faults": 0,
          "wins": 9
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 124,
          "capped_draws": 63,
          "coverage_status": "rated",
          "distinct_rated_opponents": 62,
          "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": 1466.4297670164335,
          "reasoning": "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": 31.624425793989726,
          "uncertainty": 0.9713595499957961,
          "unilateral_faults": 0,
          "wins": 29
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 118,
          "capped_draws": 86,
          "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": "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": 1444.8116248114163,
          "reasoning": "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": 28.95538217774586,
          "uncertainty": 2.084924851410568,
          "unilateral_faults": 0,
          "wins": 9
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 44,
          "capped_draws": 32,
          "coverage_status": "rated",
          "distinct_rated_opponents": 22,
          "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": "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": 9,
          "model": "poolside/laguna-s-2.1",
          "point_rating_method": "sequential_elo",
          "public_id": "E-0fab95afbec0dd98",
          "rated_matches": 44,
          "raw_elo_rating": 1439.6669918897676,
          "reasoning": "enabled",
          "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": 25.622761910534294,
          "uncertainty": 30.785599249992988,
          "unilateral_faults": 0,
          "wins": 3
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 44,
          "capped_draws": 35,
          "coverage_status": "rated",
          "distinct_rated_opponents": 22,
          "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": "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": 8,
          "model": "poolside/laguna-s-2.1",
          "point_rating_method": "sequential_elo",
          "public_id": "E-f72c72b8f264c57a",
          "rated_matches": 44,
          "raw_elo_rating": 1437.3867959450756,
          "reasoning": "enabled",
          "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": 25.352383664872303,
          "uncertainty": 30.785599249992988,
          "unilateral_faults": 0,
          "wins": 1
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 72,
          "capped_draws": 48,
          "coverage_status": "rated",
          "distinct_rated_opponents": 36,
          "draws": 48,
          "evaluated_setting_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": 19,
          "model": "qwen/qwen3.7-max",
          "point_rating_method": "sequential_elo",
          "public_id": "E-64624689e7cbd439",
          "rated_matches": 72,
          "raw_elo_rating": 1425.558769052083,
          "reasoning": "enabled",
          "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": 25.469062440505223,
          "uncertainty": 14.770573598065289,
          "unilateral_faults": 0,
          "wins": 5
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 76,
          "capped_draws": 58,
          "coverage_status": "rated",
          "distinct_rated_opponents": 38,
          "draws": 58,
          "evaluated_setting_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": 18,
          "model": "qwen/qwen3.7-plus",
          "point_rating_method": "sequential_elo",
          "public_id": "E-6c2a9942e92223c8",
          "rated_matches": 76,
          "raw_elo_rating": 1428.5564045306385,
          "reasoning": "enabled",
          "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": 25.970625978953073,
          "uncertainty": 13.230288229818967,
          "unilateral_faults": 0,
          "wins": 0
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 71,
          "capped_draws": 55,
          "coverage_status": "rated",
          "distinct_rated_opponents": 36,
          "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": "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": 12,
          "model": "thinkingmachines/inkling",
          "point_rating_method": "sequential_elo",
          "public_id": "E-9f74dab09049a473",
          "rated_matches": 71,
          "raw_elo_rating": 1442.2338469609456,
          "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": 27.407921076039756,
          "uncertainty": 15.175565098878963,
          "unilateral_faults": 0,
          "wins": 4
        },
        {
          "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": 1882.0961693922998,
          "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": 80.48164573606203,
          "uncertainty": 5.516463908214657,
          "unilateral_faults": 0,
          "wins": 87
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 70,
          "capped_draws": 50,
          "coverage_status": "rated",
          "distinct_rated_opponents": 35,
          "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": "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": 70,
          "raw_elo_rating": 1421.3852147171185,
          "reasoning": "enabled",
          "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": 24.89653094745947,
          "uncertainty": 15.58908290969266,
          "unilateral_faults": 0,
          "wins": 5
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 72,
          "capped_draws": 42,
          "coverage_status": "rated",
          "distinct_rated_opponents": 36,
          "draws": 42,
          "evaluated_setting_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": 15,
          "model": "xiaomi/mimo-v2.5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-650d06103e7fa176",
          "rated_matches": 72,
          "raw_elo_rating": 1508.237527612685,
          "reasoning": "enabled",
          "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": 35.272841692532026,
          "uncertainty": 14.770573598065289,
          "unilateral_faults": 0,
          "wins": 15
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 58,
          "capped_draws": 25,
          "coverage_status": "rated",
          "distinct_rated_opponents": 29,
          "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": "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": 32,
          "model": "xiaomi/mimo-v2.5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-b5eb7da0f5021b69",
          "rated_matches": 58,
          "raw_elo_rating": 1296.6805776772846,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "repaired",
          "score": 9.563496475865678,
          "uncertainty": 21.344455490411935,
          "unilateral_faults": 0,
          "wins": 1
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 62,
          "capped_draws": 37,
          "coverage_status": "rated",
          "distinct_rated_opponents": 31,
          "draws": 37,
          "evaluated_setting_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-bd1bb7ac29877b8f",
          "rated_matches": 62,
          "raw_elo_rating": 1347.5295489399816,
          "reasoning": "enabled",
          "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": 15.792247386975294,
          "uncertainty": 19.244078834871203,
          "unilateral_faults": 0,
          "wins": 2
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 74,
          "capped_draws": 62,
          "coverage_status": "rated",
          "distinct_rated_opponents": 37,
          "draws": 62,
          "evaluated_setting_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": 74,
          "raw_elo_rating": 1427.9759189337483,
          "reasoning": "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": 25.83019830376679,
          "uncertainty": 13.985026918962571,
          "unilateral_faults": 0,
          "wins": 1
        }
      ]
    },
    "full_freedom/baseline": {
      "GB2-01": [
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 116,
          "capped_draws": 76,
          "coverage_status": "rated",
          "distinct_rated_opponents": 57,
          "draws": 76,
          "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": 25,
          "model": "claude-opus-4-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-2e3eca63f7980fac",
          "rated_matches": 116,
          "raw_elo_rating": 1460.8178118795715,
          "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": 42.428677925307234,
          "uncertainty": 2.4750163521024238,
          "unilateral_faults": 0,
          "wins": 15
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 84,
          "capped_draws": 20,
          "coverage_status": "rated",
          "distinct_rated_opponents": 42,
          "draws": 20,
          "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": 84,
          "raw_elo_rating": 1571.0311336651146,
          "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": 53.58101009021854,
          "uncertainty": 10.482614454664043,
          "unilateral_faults": 0,
          "wins": 40
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 118,
          "capped_draws": 85,
          "coverage_status": "rated",
          "distinct_rated_opponents": 57,
          "draws": 85,
          "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": 117,
          "raw_elo_rating": 1559.7896571777924,
          "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": 53.07839841737344,
          "uncertainty": 2.2787308949161655,
          "unilateral_faults": 0,
          "wins": 18
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 116,
          "capped_draws": 16,
          "coverage_status": "rated",
          "distinct_rated_opponents": 56,
          "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": 116,
          "raw_elo_rating": 1878.8405444643897,
          "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": 87.3381487667594,
          "uncertainty": 2.4750163521024238,
          "unilateral_faults": 0,
          "wins": 91
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 84,
          "capped_draws": 66,
          "coverage_status": "rated",
          "distinct_rated_opponents": 42,
          "draws": 66,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-sonnet-5",
            "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-12T16:00:00Z",
          "losses": 10,
          "model": "claude-sonnet-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-259fc4a9e48c81f2",
          "rated_matches": 84,
          "raw_elo_rating": 1489.6057722063917,
          "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": 44.83323249072341,
          "uncertainty": 10.482614454664043,
          "unilateral_faults": 0,
          "wins": 8
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 126,
          "capped_draws": 77,
          "coverage_status": "rated",
          "distinct_rated_opponents": 58,
          "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": 28,
          "model": "cohere/north-mini-code",
          "point_rating_method": "sequential_elo",
          "public_id": "E-194759b182ce3244",
          "rated_matches": 126,
          "raw_elo_rating": 1508.2988051809066,
          "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": 47.689326403384385,
          "uncertainty": 0.617825470805693,
          "unilateral_faults": 0,
          "wins": 21
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 96,
          "capped_draws": 21,
          "coverage_status": "rated",
          "distinct_rated_opponents": 46,
          "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": 73,
          "model": "cohere/north-mini-code",
          "point_rating_method": "sequential_elo",
          "public_id": "E-c309b463b29efb71",
          "rated_matches": 96,
          "raw_elo_rating": 1090.3276521844061,
          "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": 2.235383984912514,
          "uncertainty": 7.017308256680951,
          "unilateral_faults": 0,
          "wins": 2
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 124,
          "capped_draws": 46,
          "coverage_status": "rated",
          "distinct_rated_opponents": 60,
          "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": 44,
          "model": "deepseek/deepseek-v4-pro",
          "point_rating_method": "sequential_elo",
          "public_id": "E-e121525dd1846069",
          "rated_matches": 124,
          "raw_elo_rating": 1488.5540474275292,
          "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": 45.53770120402753,
          "uncertainty": 0.9713595499957961,
          "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": 1181.3686609045587,
          "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": 11.482216539302486,
          "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": "low",
          "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": 44,
          "capped_draws": 15,
          "coverage_status": "rated",
          "distinct_rated_opponents": 22,
          "draws": 15,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "minimal",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "google/gemini-3.5-flash-lite",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 7,
          "model": "google/gemini-3.5-flash-lite",
          "point_rating_method": "sequential_elo",
          "public_id": "E-21c0edac8ac36f2e",
          "rated_matches": 44,
          "raw_elo_rating": 1578.435818592523,
          "reasoning": "minimal",
          "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": 52.63154842186275,
          "uncertainty": 30.785599249992988,
          "unilateral_faults": 0,
          "wins": 22
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 34,
          "capped_draws": 11,
          "coverage_status": "under_covered",
          "distinct_rated_opponents": 17,
          "draws": 11,
          "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": 13,
          "model": "google/gemini-3.5-flash-lite",
          "point_rating_method": "sequential_elo",
          "public_id": "E-cf51875df5447bc2",
          "rated_matches": 34,
          "raw_elo_rating": 1475.5613872584288,
          "reasoning": "minimal",
          "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": 40.72170032496317,
          "uncertainty": 40.76542547285167,
          "unilateral_faults": 0,
          "wins": 10
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 42,
          "capped_draws": 15,
          "coverage_status": "rated",
          "distinct_rated_opponents": 21,
          "draws": 15,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "minimal",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "google/gemini-3.6-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-e0c4f14c94c0a42a",
          "rated_matches": 42,
          "raw_elo_rating": 1494.6627753914672,
          "reasoning": "minimal",
          "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": 43.48426688660894,
          "uncertainty": 32.49928516630233,
          "unilateral_faults": 0,
          "wins": 15
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 40,
          "capped_draws": 12,
          "coverage_status": "rated",
          "distinct_rated_opponents": 20,
          "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": "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": 15,
          "model": "google/gemini-3.6-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-e9733de94d982ade",
          "rated_matches": 40,
          "raw_elo_rating": 1426.337846925775,
          "reasoning": "minimal",
          "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": 35.985974326056116,
          "uncertainty": 34.33688094430304,
          "unilateral_faults": 0,
          "wins": 13
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 118,
          "capped_draws": 25,
          "coverage_status": "rated",
          "distinct_rated_opponents": 57,
          "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": 38,
          "model": "google/gemma-4-31b-it",
          "point_rating_method": "sequential_elo",
          "public_id": "E-caaa54d3c88e6570",
          "rated_matches": 118,
          "raw_elo_rating": 1479.4739373802697,
          "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": 44.46648998691777,
          "uncertainty": 2.084924851410568,
          "unilateral_faults": 0,
          "wins": 55
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 110,
          "capped_draws": 5,
          "coverage_status": "rated",
          "distinct_rated_opponents": 54,
          "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": 47,
          "model": "gpt-4.1",
          "point_rating_method": "sequential_elo",
          "public_id": "E-f50ec6b60d5b85da",
          "rated_matches": 109,
          "raw_elo_rating": 1591.5902539682866,
          "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": 56.353504319456164,
          "uncertainty": 3.9231294622796127,
          "unilateral_faults": 1,
          "wins": 57
        },
        {
          "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": "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": 22,
          "model": "gpt-4.1-nano",
          "point_rating_method": "sequential_elo",
          "public_id": "E-e117cfcfd3d0bf38",
          "rated_matches": 82,
          "raw_elo_rating": 1517.321654013368,
          "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": 47.75501155028078,
          "uncertainty": 11.132129994845172,
          "unilateral_faults": 0,
          "wins": 34
        },
        {
          "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": "low",
          "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": 2,
          "coverage_status": "rated",
          "distinct_rated_opponents": 46,
          "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": 92,
          "raw_elo_rating": 2000.7945640968424,
          "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": 99.95680517171921,
          "uncertainty": 8.09758473652126,
          "unilateral_faults": 0,
          "wins": 84
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 106,
          "capped_draws": 40,
          "coverage_status": "rated",
          "distinct_rated_opponents": 52,
          "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": 44,
          "model": "gpt-5.4-mini",
          "point_rating_method": "sequential_elo",
          "public_id": "E-ea1cb793f92b3cff",
          "rated_matches": 106,
          "raw_elo_rating": 1392.215360433307,
          "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": 34.877002635313595,
          "uncertainty": 4.586824452283178,
          "unilateral_faults": 0,
          "wins": 22
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 88,
          "capped_draws": 19,
          "coverage_status": "rated",
          "distinct_rated_opponents": 43,
          "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": 22,
          "model": "gpt-5.4-nano",
          "point_rating_method": "sequential_elo",
          "public_id": "E-9eb27042bf28d67c",
          "rated_matches": 88,
          "raw_elo_rating": 1626.5972093725554,
          "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": 59.65659286939674,
          "uncertainty": 9.249894000318006,
          "unilateral_faults": 0,
          "wins": 47
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 108,
          "capped_draws": 32,
          "coverage_status": "rated",
          "distinct_rated_opponents": 50,
          "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-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-a8887794a1195b75",
          "rated_matches": 102,
          "raw_elo_rating": 1578.2811745197378,
          "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": 54.78672741992332,
          "uncertainty": 5.516463908214657,
          "unilateral_faults": 0,
          "wins": 33
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 120,
          "capped_draws": 90,
          "coverage_status": "rated",
          "distinct_rated_opponents": 59,
          "draws": 90,
          "evaluated_setting_identity": {
            "canonical_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": 120,
          "raw_elo_rating": 1515.5640194755229,
          "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": 48.376451029853435,
          "uncertainty": 1.7045454545454586,
          "unilateral_faults": 0,
          "wins": 11
        },
        {
          "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": 1277.2755591791679,
          "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": 22.385721389270085,
          "uncertainty": 6.25,
          "unilateral_faults": 0,
          "wins": 14
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 92,
          "capped_draws": 11,
          "coverage_status": "rated",
          "distinct_rated_opponents": 43,
          "draws": 11,
          "evaluated_setting_identity": {
            "canonical_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": 28,
          "model": "gpt-5.6-sol",
          "point_rating_method": "sequential_elo",
          "public_id": "E-890c38b8e811c121",
          "rated_matches": 86,
          "raw_elo_rating": 1555.171019743832,
          "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": 51.9309965364074,
          "uncertainty": 9.855626741889738,
          "unilateral_faults": 0,
          "wins": 47
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 94,
          "capped_draws": 30,
          "coverage_status": "rated",
          "distinct_rated_opponents": 46,
          "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": 35,
          "model": "gpt-5.6-terra",
          "point_rating_method": "sequential_elo",
          "public_id": "E-40742129939a44b5",
          "rated_matches": 94,
          "raw_elo_rating": 1555.7694478579945,
          "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": 52.193541012565454,
          "uncertainty": 7.54891760425771,
          "unilateral_faults": 0,
          "wins": 29
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 158,
          "capped_draws": 58,
          "coverage_status": "rated",
          "distinct_rated_opponents": 64,
          "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": 1381.054611496271,
          "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": 34.424349154668995,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 51
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 150,
          "capped_draws": 43,
          "coverage_status": "rated",
          "distinct_rated_opponents": 58,
          "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": 65,
          "model": "inclusionai/ling-3.0-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-f9af396559c3a1cd",
          "rated_matches": 150,
          "raw_elo_rating": 1489.4165078728365,
          "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": 45.976888692310695,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 42
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 114,
          "capped_draws": 34,
          "coverage_status": "rated",
          "distinct_rated_opponents": 54,
          "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": 46,
          "model": "meituan/longcat-2.0",
          "point_rating_method": "sequential_elo",
          "public_id": "E-9f5585b5fd96f2c3",
          "rated_matches": 114,
          "raw_elo_rating": 1434.1444270156533,
          "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": 39.52867611705157,
          "uncertainty": 2.875240412015687,
          "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": 1380.9335045784128,
          "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": 34.006079518097124,
          "uncertainty": 0.617825470805693,
          "unilateral_faults": 0,
          "wins": 31
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 122,
          "capped_draws": 24,
          "coverage_status": "rated",
          "distinct_rated_opponents": 60,
          "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": 38,
          "model": "minimax/minimax-m3",
          "point_rating_method": "sequential_elo",
          "public_id": "E-444510032bc433fc",
          "rated_matches": 122,
          "raw_elo_rating": 1543.4553724122525,
          "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": 51.404796674852406,
          "uncertainty": 1.3334817333716131,
          "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": 1483.4317022040432,
          "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": 44.576050565533166,
          "uncertainty": 5.757377148833722,
          "unilateral_faults": 35,
          "wins": 43
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 66,
          "capped_draws": 47,
          "coverage_status": "rated",
          "distinct_rated_opponents": 33,
          "draws": 47,
          "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": 7,
          "model": "moonshotai/kimi-k3",
          "point_rating_method": "sequential_elo",
          "public_id": "E-fb8801908d28001f",
          "rated_matches": 66,
          "raw_elo_rating": 1543.8316411636547,
          "reasoning": "low",
          "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": 50.06997031510964,
          "uncertainty": 17.33472217815261,
          "unilateral_faults": 0,
          "wins": 12
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 82,
          "capped_draws": 14,
          "coverage_status": "rated",
          "distinct_rated_opponents": 41,
          "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": 40,
          "model": "nvidia/nemotron-3-ultra-550b-a55b",
          "point_rating_method": "sequential_elo",
          "public_id": "E-0ce5e196701b51f3",
          "rated_matches": 82,
          "raw_elo_rating": 1574.046272202658,
          "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": 53.84911215292571,
          "uncertainty": 11.132129994845172,
          "unilateral_faults": 0,
          "wins": 28
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 50,
          "capped_draws": 18,
          "coverage_status": "rated",
          "distinct_rated_opponents": 25,
          "draws": 18,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "low",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "o3",
            "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-21T14:20:15Z",
          "losses": 27,
          "model": "o3",
          "point_rating_method": "sequential_elo",
          "public_id": "E-cb2bd51b4adfa607",
          "rated_matches": 50,
          "raw_elo_rating": 1346.0195035899546,
          "reasoning": "low",
          "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": 28.05096232465229,
          "uncertainty": 26.264004201400486,
          "unilateral_faults": 0,
          "wins": 5
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 58,
          "capped_draws": 14,
          "coverage_status": "rated",
          "distinct_rated_opponents": 29,
          "draws": 14,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "low",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "openai/gpt-oss-120b",
            "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-21T14:20:15Z",
          "losses": 32,
          "model": "openai/gpt-oss-120b",
          "point_rating_method": "sequential_elo",
          "public_id": "E-55f6c0e3dc8a8065",
          "rated_matches": 58,
          "raw_elo_rating": 1353.7738933916733,
          "reasoning": "low",
          "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": 29.30685815347161,
          "uncertainty": 21.344455490411935,
          "unilateral_faults": 0,
          "wins": 12
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 118,
          "capped_draws": 20,
          "coverage_status": "rated",
          "distinct_rated_opponents": 58,
          "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": 57,
          "model": "poolside/laguna-s-2.1",
          "point_rating_method": "sequential_elo",
          "public_id": "E-8461eb1b16e40129",
          "rated_matches": 118,
          "raw_elo_rating": 1588.875259183409,
          "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": 56.21981125046297,
          "uncertainty": 2.084924851410568,
          "unilateral_faults": 0,
          "wins": 41
        },
        {
          "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": "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": 45,
          "model": "poolside/laguna-s-2.1",
          "point_rating_method": "sequential_elo",
          "public_id": "E-c58ec61528547516",
          "rated_matches": 116,
          "raw_elo_rating": 1458.5679351295464,
          "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": 42.186966730135296,
          "uncertainty": 2.4750163521024238,
          "unilateral_faults": 0,
          "wins": 37
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 102,
          "capped_draws": 23,
          "coverage_status": "rated",
          "distinct_rated_opponents": 48,
          "draws": 23,
          "evaluated_setting_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": 96,
          "raw_elo_rating": 1572.4078988417914,
          "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": 54.02675103959072,
          "uncertainty": 7.017308256680951,
          "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": 1351.2113457571206,
          "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": 30.350197668676998,
          "uncertainty": 6.001859510499461,
          "unilateral_faults": 0,
          "wins": 19
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 102,
          "capped_draws": 17,
          "coverage_status": "rated",
          "distinct_rated_opponents": 48,
          "draws": 17,
          "evaluated_setting_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": 96,
          "raw_elo_rating": 1734.2538039468136,
          "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": 71.41435556334146,
          "uncertainty": 7.017308256680951,
          "unilateral_faults": 0,
          "wins": 60
        },
        {
          "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": 1281.5213970678337,
          "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": 23.16631134735838,
          "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": 1146.1984499521122,
          "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": 8.5937521216808,
          "uncertainty": 2.875240412015687,
          "unilateral_faults": 0,
          "wins": 6
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 68,
          "capped_draws": 44,
          "coverage_status": "rated",
          "distinct_rated_opponents": 34,
          "draws": 44,
          "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": 6,
          "model": "x-ai/grok-4.5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-7ee1b68d1249ac22",
          "rated_matches": 68,
          "raw_elo_rating": 1580.8420803513893,
          "reasoning": "low",
          "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": 54.12276257623396,
          "uncertainty": 16.4429265428846,
          "unilateral_faults": 0,
          "wins": 18
        },
        {
          "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": "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": 90,
          "raw_elo_rating": 1576.888139347102,
          "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": 54.36652896747432,
          "uncertainty": 8.664241836095918,
          "unilateral_faults": 0,
          "wins": 44
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 118,
          "capped_draws": 27,
          "coverage_status": "rated",
          "distinct_rated_opponents": 58,
          "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": 49,
          "model": "xiaomi/mimo-v2.5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-912a4a40bbdcbd45",
          "rated_matches": 118,
          "raw_elo_rating": 1521.4048391771312,
          "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": 48.97125603147698,
          "uncertainty": 2.084924851410568,
          "unilateral_faults": 0,
          "wins": 42
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 98,
          "capped_draws": 29,
          "coverage_status": "rated",
          "distinct_rated_opponents": 49,
          "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": 41,
          "model": "xiaomi/mimo-v2.5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-a168350bd057f924",
          "rated_matches": 98,
          "raw_elo_rating": 1437.9016164420188,
          "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": 39.620624777836554,
          "uncertainty": 6.501890762960602,
          "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": 1427.5356647847705,
          "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": 38.853074260758646,
          "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": 1481.5688155862535,
          "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": 43.91397389925815,
          "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": 1243.092112701758,
          "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": 18.048490123576414,
          "uncertainty": 13.985026918962571,
          "unilateral_faults": 0,
          "wins": 22
        }
      ],
      "GB2-02": [
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 90,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 45,
          "draws": 74,
          "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": 90,
          "raw_elo_rating": 1493.9783604804352,
          "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": 28.975930507597035,
          "uncertainty": 8.664241836095918,
          "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": 1470.3374865351009,
          "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": 22.761732969686722,
          "uncertainty": 13.230288229818967,
          "unilateral_faults": 0,
          "wins": 3
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 90,
          "capped_draws": 0,
          "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": "2026-07-25T10:50:00Z",
          "losses": 10,
          "model": "claude-opus-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-51ddad48e10b006f",
          "rated_matches": 90,
          "raw_elo_rating": 1671.2479236604809,
          "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": 69.336439953367,
          "uncertainty": 8.664241836095918,
          "unilateral_faults": 0,
          "wins": 56
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 88,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 44,
          "draws": 46,
          "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": 88,
          "raw_elo_rating": 1643.7537400063634,
          "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": 62.96992663548684,
          "uncertainty": 9.249894000318006,
          "unilateral_faults": 0,
          "wins": 38
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 82,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 41,
          "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": "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": 82,
          "raw_elo_rating": 1471.1514124728146,
          "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": 23.329211401413826,
          "uncertainty": 11.132129994845172,
          "unilateral_faults": 0,
          "wins": 1
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 86,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 43,
          "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": "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": 86,
          "raw_elo_rating": 1479.248896520903,
          "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": 25.40534241954475,
          "uncertainty": 9.855626741889738,
          "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": 1482.8419989760441,
          "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": 24.513374734358962,
          "uncertainty": 19.244078834871203,
          "unilateral_faults": 0,
          "wins": 1
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 26,
          "capped_draws": 0,
          "coverage_status": "under_covered",
          "distinct_rated_opponents": 13,
          "draws": 22,
          "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": 3,
          "model": "google/gemini-3.5-flash-lite",
          "point_rating_method": "sequential_elo",
          "public_id": "E-1010911d64a09b68",
          "rated_matches": 26,
          "raw_elo_rating": 1479.4002573381329,
          "reasoning": "minimal",
          "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": 17.676975981941407,
          "uncertainty": 52.475044864937615,
          "unilateral_faults": 0,
          "wins": 1
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 30,
          "capped_draws": 0,
          "coverage_status": "under_covered",
          "distinct_rated_opponents": 15,
          "draws": 29,
          "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": 1,
          "model": "google/gemini-3.5-flash-lite",
          "point_rating_method": "sequential_elo",
          "public_id": "E-e65fdcb71f09a611",
          "rated_matches": 30,
          "raw_elo_rating": 1479.348920615594,
          "reasoning": "minimal",
          "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": 18.835081695128604,
          "uncertainty": 46.05265101338746,
          "unilateral_faults": 0,
          "wins": 0
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 28,
          "capped_draws": 0,
          "coverage_status": "under_covered",
          "distinct_rated_opponents": 14,
          "draws": 27,
          "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": 1,
          "model": "google/gemini-3.6-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-4492f6d65cd6280b",
          "rated_matches": 28,
          "raw_elo_rating": 1482.3135878183718,
          "reasoning": "minimal",
          "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": 18.95544468148222,
          "uncertainty": 49.09766908852594,
          "unilateral_faults": 0,
          "wins": 0
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 28,
          "capped_draws": 0,
          "coverage_status": "under_covered",
          "distinct_rated_opponents": 14,
          "draws": 27,
          "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": 1,
          "model": "google/gemini-3.6-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-9c8b43dc41bad760",
          "rated_matches": 28,
          "raw_elo_rating": 1484.8758512553966,
          "reasoning": "minimal",
          "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": 19.538817573012135,
          "uncertainty": 49.09766908852594,
          "unilateral_faults": 0,
          "wins": 0
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 84,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 42,
          "draws": 70,
          "evaluated_setting_identity": {
            "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": 84,
          "raw_elo_rating": 1463.4359726589596,
          "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": 21.690874544258786,
          "uncertainty": 10.482614454664043,
          "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": "low",
          "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": 84,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 41,
          "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",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_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": 84,
          "raw_elo_rating": 1467.3031221858107,
          "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": 22.571342246704436,
          "uncertainty": 10.482614454664043,
          "unilateral_faults": 0,
          "wins": 1
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 84,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 41,
          "draws": 82,
          "evaluated_setting_identity": {
            "canonical_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": 84,
          "raw_elo_rating": 1469.565751019137,
          "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": 23.086494711467868,
          "uncertainty": 10.482614454664043,
          "unilateral_faults": 0,
          "wins": 0
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 86,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 43,
          "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-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": 86,
          "raw_elo_rating": 1467.2273330893977,
          "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": 22.668288095462078,
          "uncertainty": 9.855626741889738,
          "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": 1475.5653849402343,
          "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": 24.56668517191457,
          "uncertainty": 9.855626741889738,
          "unilateral_faults": 0,
          "wins": 4
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 82,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 41,
          "draws": 73,
          "evaluated_setting_identity": {
            "canonical_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": 82,
          "raw_elo_rating": 1477.8084557546495,
          "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": 24.844878577648164,
          "uncertainty": 11.132129994845172,
          "unilateral_faults": 0,
          "wins": 0
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 84,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 42,
          "draws": 82,
          "evaluated_setting_identity": {
            "canonical_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": 84,
          "raw_elo_rating": 1475.3176618766922,
          "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": 24.39608248464808,
          "uncertainty": 10.482614454664043,
          "unilateral_faults": 0,
          "wins": 0
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 70,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 35,
          "draws": 56,
          "evaluated_setting_identity": {
            "canonical_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": 70,
          "raw_elo_rating": 1495.2258908916226,
          "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": 27.998655419890518,
          "uncertainty": 15.58908290969266,
          "unilateral_faults": 0,
          "wins": 5
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 100,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 50,
          "draws": 87,
          "evaluated_setting_identity": {
            "canonical_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": 100,
          "raw_elo_rating": 1502.7441141687189,
          "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": 31.456640462802426,
          "uncertainty": 6.001859510499461,
          "unilateral_faults": 0,
          "wins": 4
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 118,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 51,
          "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": 1459.7462631719882,
          "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": 22.380386424640683,
          "uncertainty": 2.084924851410568,
          "unilateral_faults": 0,
          "wins": 1
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 98,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 49,
          "draws": 93,
          "evaluated_setting_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": 98,
          "raw_elo_rating": 1471.8760079780336,
          "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": 24.33755198695994,
          "uncertainty": 6.501890762960602,
          "unilateral_faults": 0,
          "wins": 0
        },
        {
          "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": 1462.4496711139095,
          "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": 20.685292976640326,
          "uncertainty": 14.770573598065289,
          "unilateral_faults": 0,
          "wins": 0
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 52,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 26,
          "draws": 47,
          "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": 3,
          "model": "moonshotai/kimi-k3",
          "point_rating_method": "sequential_elo",
          "public_id": "E-d3d3da42e99695b1",
          "rated_matches": 52,
          "raw_elo_rating": 1485.1516516180754,
          "reasoning": "low",
          "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": 24.003531501710604,
          "uncertainty": 24.930281974344517,
          "unilateral_faults": 0,
          "wins": 2
        },
        {
          "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": 1464.2426317683783,
          "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": 21.874533667805792,
          "uncertainty": 10.482614454664043,
          "unilateral_faults": 0,
          "wins": 2
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 104,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 51,
          "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": "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": 104,
          "raw_elo_rating": 1474.448849917776,
          "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": 25.188695148003053,
          "uncertainty": 5.045003647426665,
          "unilateral_faults": 0,
          "wins": 3
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 76,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 38,
          "draws": 62,
          "evaluated_setting_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": 76,
          "raw_elo_rating": 1491.6324167926382,
          "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": 27.610135698210527,
          "uncertainty": 13.230288229818967,
          "unilateral_faults": 0,
          "wins": 8
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 90,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 44,
          "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": "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": 0,
          "model": "qwen/qwen3.7-plus",
          "point_rating_method": "sequential_elo",
          "public_id": "E-010dafcd7561851a",
          "rated_matches": 90,
          "raw_elo_rating": 1472.4062283762817,
          "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": 24.06441481400451,
          "uncertainty": 8.664241836095918,
          "unilateral_faults": 0,
          "wins": 0
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 70,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 35,
          "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": "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": 70,
          "raw_elo_rating": 1454.0917807935598,
          "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": 18.633293372543374,
          "uncertainty": 15.58908290969266,
          "unilateral_faults": 0,
          "wins": 0
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 100,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 49,
          "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": "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": 100,
          "raw_elo_rating": 1496.1585038473304,
          "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": 29.957237052457256,
          "uncertainty": 6.001859510499461,
          "unilateral_faults": 0,
          "wins": 2
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 38,
          "capped_draws": 0,
          "coverage_status": "under_covered",
          "distinct_rated_opponents": 19,
          "draws": 31,
          "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": 5,
          "model": "x-ai/grok-4.5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-88ab68f664bd3ea0",
          "rated_matches": 38,
          "raw_elo_rating": 1486.799452161452,
          "reasoning": "low",
          "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": 22.305222241021823,
          "uncertainty": 36.31407690254356,
          "unilateral_faults": 0,
          "wins": 2
        },
        {
          "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": "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": 64,
          "raw_elo_rating": 1474.2125218481146,
          "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": 22.726527476576994,
          "uncertainty": 18.26736729460423,
          "unilateral_faults": 0,
          "wins": 0
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 76,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 38,
          "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": "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": 76,
          "raw_elo_rating": 1499.0331584380926,
          "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": 29.295127175194555,
          "uncertainty": 13.230288229818967,
          "unilateral_faults": 0,
          "wins": 5
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 64,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 32,
          "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": "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": 5,
          "model": "z-ai/glm-5.2",
          "point_rating_method": "sequential_elo",
          "public_id": "E-4959351a96fd2b82",
          "rated_matches": 64,
          "raw_elo_rating": 1452.3700253768327,
          "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": 17.75345556657859,
          "uncertainty": 18.26736729460423,
          "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": 1478.1676330281302,
          "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": 23.44912102035759,
          "uncertainty": 19.244078834871203,
          "unilateral_faults": 0,
          "wins": 1
        }
      ],
      "GB2-03": [
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 88,
          "capped_draws": 13,
          "coverage_status": "rated",
          "distinct_rated_opponents": 44,
          "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-4-5",
            "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": 88,
          "raw_elo_rating": 1518.8257098927816,
          "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": 43.90185636252289,
          "uncertainty": 9.249894000318006,
          "unilateral_faults": 0,
          "wins": 13
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 84,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 42,
          "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": 31,
          "model": "claude-opus-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-49aaba66f6b19080",
          "rated_matches": 84,
          "raw_elo_rating": 1647.928081769382,
          "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": 63.44448907504303,
          "uncertainty": 10.482614454664043,
          "unilateral_faults": 0,
          "wins": 42
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 88,
          "capped_draws": 1,
          "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-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": 23,
          "model": "claude-opus-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-ecf847457e616425",
          "rated_matches": 88,
          "raw_elo_rating": 1524.3683554934487,
          "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": 44.74732236153788,
          "uncertainty": 9.249894000318006,
          "unilateral_faults": 0,
          "wins": 42
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 86,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 43,
          "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": "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": 27,
          "model": "deepseek/deepseek-v4-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-ae9d59ec3a8a1d63",
          "rated_matches": 86,
          "raw_elo_rating": 1438.523896395089,
          "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": 31.578832477807513,
          "uncertainty": 9.855626741889738,
          "unilateral_faults": 0,
          "wins": 20
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 62,
          "capped_draws": 1,
          "coverage_status": "rated",
          "distinct_rated_opponents": 29,
          "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": 62,
          "raw_elo_rating": 1406.28947900497,
          "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": 25.516168554327326,
          "uncertainty": 19.244078834871203,
          "unilateral_faults": 0,
          "wins": 15
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 34,
          "capped_draws": 1,
          "coverage_status": "under_covered",
          "distinct_rated_opponents": 17,
          "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": "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": 7,
          "model": "google/gemini-3.5-flash-lite",
          "point_rating_method": "sequential_elo",
          "public_id": "E-28274045fbc35ae9",
          "rated_matches": 34,
          "raw_elo_rating": 1548.3739228344587,
          "reasoning": "minimal",
          "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": 44.56323026177964,
          "uncertainty": 40.76542547285167,
          "unilateral_faults": 0,
          "wins": 13
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 34,
          "capped_draws": 2,
          "coverage_status": "under_covered",
          "distinct_rated_opponents": 17,
          "draws": 8,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "minimal",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "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-6743f1c221046d65",
          "rated_matches": 34,
          "raw_elo_rating": 1590.360541675656,
          "reasoning": "minimal",
          "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": 50.96779970413437,
          "uncertainty": 40.76542547285167,
          "unilateral_faults": 0,
          "wins": 18
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 34,
          "capped_draws": 2,
          "coverage_status": "under_covered",
          "distinct_rated_opponents": 17,
          "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": "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-80b8c1a18d6dd238",
          "rated_matches": 34,
          "raw_elo_rating": 1511.5768806057672,
          "reasoning": "minimal",
          "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": 38.95027025853986,
          "uncertainty": 40.76542547285167,
          "unilateral_faults": 0,
          "wins": 11
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 82,
          "capped_draws": 2,
          "coverage_status": "rated",
          "distinct_rated_opponents": 41,
          "draws": 27,
          "evaluated_setting_identity": {
            "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": 30,
          "model": "gpt-4.1",
          "point_rating_method": "sequential_elo",
          "public_id": "E-c7da9914f86ee846",
          "rated_matches": 82,
          "raw_elo_rating": 1525.8397181307937,
          "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": 44.74207105225406,
          "uncertainty": 11.132129994845172,
          "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": "low",
          "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": 80,
          "capped_draws": 4,
          "coverage_status": "rated",
          "distinct_rated_opponents": 40,
          "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": 80,
          "raw_elo_rating": 1602.3083636563829,
          "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": 56.324293275397885,
          "uncertainty": 11.805555555555554,
          "unilateral_faults": 0,
          "wins": 31
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 82,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 41,
          "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": 4,
          "model": "gpt-5.4-mini",
          "point_rating_method": "sequential_elo",
          "public_id": "E-35117a2e624d7970",
          "rated_matches": 82,
          "raw_elo_rating": 1480.7237122491786,
          "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": 37.860150083019626,
          "uncertainty": 11.132129994845172,
          "unilateral_faults": 0,
          "wins": 1
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 88,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 44,
          "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-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": 88,
          "raw_elo_rating": 1508.3524419563448,
          "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": 42.304281381765435,
          "uncertainty": 9.249894000318006,
          "unilateral_faults": 0,
          "wins": 28
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 80,
          "capped_draws": 7,
          "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-5.5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_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-5.5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-446036823932df16",
          "rated_matches": 80,
          "raw_elo_rating": 1453.647103601243,
          "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": 33.64775037461809,
          "uncertainty": 11.805555555555554,
          "unilateral_faults": 0,
          "wins": 18
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 76,
          "capped_draws": 1,
          "coverage_status": "rated",
          "distinct_rated_opponents": 37,
          "draws": 37,
          "evaluated_setting_identity": {
            "canonical_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-d192bb239087b778",
          "rated_matches": 76,
          "raw_elo_rating": 1476.915508520607,
          "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": 37.02321330902676,
          "uncertainty": 13.230288229818967,
          "unilateral_faults": 0,
          "wins": 21
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 80,
          "capped_draws": 14,
          "coverage_status": "rated",
          "distinct_rated_opponents": 40,
          "draws": 41,
          "evaluated_setting_identity": {
            "canonical_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": 24,
          "model": "gpt-5.6-sol",
          "point_rating_method": "sequential_elo",
          "public_id": "E-527999604d620080",
          "rated_matches": 80,
          "raw_elo_rating": 1451.199816272659,
          "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": 33.27444521040391,
          "uncertainty": 11.805555555555554,
          "unilateral_faults": 0,
          "wins": 15
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 78,
          "capped_draws": 8,
          "coverage_status": "rated",
          "distinct_rated_opponents": 39,
          "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-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": 23,
          "model": "gpt-5.6-terra",
          "point_rating_method": "sequential_elo",
          "public_id": "E-c2f0f8f062659e83",
          "rated_matches": 78,
          "raw_elo_rating": 1525.7262366492885,
          "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": 44.55730234033761,
          "uncertainty": 12.5043950463012,
          "unilateral_faults": 0,
          "wins": 20
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 100,
          "capped_draws": 1,
          "coverage_status": "rated",
          "distinct_rated_opponents": 41,
          "draws": 39,
          "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": 100,
          "raw_elo_rating": 1327.6233920315324,
          "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": 15.132530666228146,
          "uncertainty": 6.001859510499461,
          "unilateral_faults": 0,
          "wins": 14
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 96,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 39,
          "draws": 45,
          "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": 96,
          "raw_elo_rating": 1440.3263728765553,
          "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": 32.20014118958681,
          "uncertainty": 7.017308256680951,
          "unilateral_faults": 0,
          "wins": 21
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 78,
          "capped_draws": 5,
          "coverage_status": "rated",
          "distinct_rated_opponents": 37,
          "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": 32,
          "model": "meituan/longcat-2.0",
          "point_rating_method": "sequential_elo",
          "public_id": "E-198e8ddfe9f7ce20",
          "rated_matches": 78,
          "raw_elo_rating": 1348.6392568902086,
          "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": 17.54474713808228,
          "uncertainty": 12.5043950463012,
          "unilateral_faults": 0,
          "wins": 11
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 84,
          "capped_draws": 9,
          "coverage_status": "rated",
          "distinct_rated_opponents": 40,
          "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": 19,
          "model": "meituan/longcat-2.0",
          "point_rating_method": "sequential_elo",
          "public_id": "E-84709c769628f9a2",
          "rated_matches": 84,
          "raw_elo_rating": 1472.8951815703904,
          "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": 36.74525977389118,
          "uncertainty": 10.482614454664043,
          "unilateral_faults": 0,
          "wins": 26
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 90,
          "capped_draws": 1,
          "coverage_status": "rated",
          "distinct_rated_opponents": 45,
          "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": "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": 25,
          "model": "minimax/minimax-m3",
          "point_rating_method": "sequential_elo",
          "public_id": "E-44cc758f104a74ab",
          "rated_matches": 90,
          "raw_elo_rating": 1480.8755147233076,
          "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": 38.18446384616218,
          "uncertainty": 8.664241836095918,
          "unilateral_faults": 0,
          "wins": 32
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 38,
          "capped_draws": 0,
          "coverage_status": "under_covered",
          "distinct_rated_opponents": 19,
          "draws": 7,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "low",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "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": 3,
          "model": "moonshotai/kimi-k3",
          "point_rating_method": "sequential_elo",
          "public_id": "E-09859be1b47131a0",
          "rated_matches": 38,
          "raw_elo_rating": 1710.1148854952874,
          "reasoning": "low",
          "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": 69.77813046280103,
          "uncertainty": 36.31407690254356,
          "unilateral_faults": 0,
          "wins": 28
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 66,
          "capped_draws": 7,
          "coverage_status": "rated",
          "distinct_rated_opponents": 31,
          "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": 14,
          "model": "nex-agi/nex-n2-pro",
          "point_rating_method": "sequential_elo",
          "public_id": "E-a05d4cef5f788f16",
          "rated_matches": 66,
          "raw_elo_rating": 1450.3899699523217,
          "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": 32.476184640834816,
          "uncertainty": 17.33472217815261,
          "unilateral_faults": 0,
          "wins": 9
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 48,
          "capped_draws": 6,
          "coverage_status": "rated",
          "distinct_rated_opponents": 24,
          "draws": 36,
          "evaluated_setting_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": 48,
          "raw_elo_rating": 1414.2361193788938,
          "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": 25.69906909498186,
          "uncertainty": 27.678571428571434,
          "unilateral_faults": 0,
          "wins": 3
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 44,
          "capped_draws": 2,
          "coverage_status": "rated",
          "distinct_rated_opponents": 22,
          "draws": 28,
          "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": 13,
          "model": "openai/gpt-oss-120b",
          "point_rating_method": "sequential_elo",
          "public_id": "E-c90a449ff5e7b79a",
          "rated_matches": 44,
          "raw_elo_rating": 1380.5301299249386,
          "reasoning": "low",
          "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": 20.17846046223821,
          "uncertainty": 30.785599249992988,
          "unilateral_faults": 0,
          "wins": 3
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 70,
          "capped_draws": 1,
          "coverage_status": "rated",
          "distinct_rated_opponents": 35,
          "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": "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": 18,
          "model": "poolside/laguna-s-2.1",
          "point_rating_method": "sequential_elo",
          "public_id": "E-7acc466aeae25d41",
          "rated_matches": 70,
          "raw_elo_rating": 1463.857478465486,
          "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": 34.74351767331942,
          "uncertainty": 15.58908290969266,
          "unilateral_faults": 0,
          "wins": 19
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 86,
          "capped_draws": 5,
          "coverage_status": "rated",
          "distinct_rated_opponents": 43,
          "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": "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": 86,
          "raw_elo_rating": 1445.8680017614674,
          "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": 32.69909017202293,
          "uncertainty": 9.855626741889738,
          "unilateral_faults": 0,
          "wins": 20
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 66,
          "capped_draws": 6,
          "coverage_status": "rated",
          "distinct_rated_opponents": 31,
          "draws": 50,
          "evaluated_setting_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": 66,
          "raw_elo_rating": 1437.7587628203037,
          "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": 30.549441181835455,
          "uncertainty": 17.33472217815261,
          "unilateral_faults": 0,
          "wins": 6
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 84,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 41,
          "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": "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": 84,
          "raw_elo_rating": 1450.2133962405546,
          "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": 33.28541772823972,
          "uncertainty": 10.482614454664043,
          "unilateral_faults": 0,
          "wins": 29
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 78,
          "capped_draws": 6,
          "coverage_status": "rated",
          "distinct_rated_opponents": 37,
          "draws": 42,
          "evaluated_setting_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": 78,
          "raw_elo_rating": 1450.0176958204406,
          "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": 33.00884665373824,
          "uncertainty": 12.5043950463012,
          "unilateral_faults": 0,
          "wins": 18
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 86,
          "capped_draws": 9,
          "coverage_status": "rated",
          "distinct_rated_opponents": 43,
          "draws": 36,
          "evaluated_setting_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": 86,
          "raw_elo_rating": 1603.7282506860715,
          "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": 56.77883163081865,
          "uncertainty": 9.855626741889738,
          "unilateral_faults": 0,
          "wins": 31
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 40,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 20,
          "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": "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-02f7e54245bd5c85",
          "rated_matches": 40,
          "raw_elo_rating": 1339.5741281314313,
          "reasoning": "low",
          "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": 13.497734328869447,
          "uncertainty": 34.33688094430304,
          "unilateral_faults": 0,
          "wins": 3
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 86,
          "capped_draws": 1,
          "coverage_status": "rated",
          "distinct_rated_opponents": 43,
          "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": 86,
          "raw_elo_rating": 1463.1084595149894,
          "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": 35.328921102635334,
          "uncertainty": 9.855626741889738,
          "unilateral_faults": 0,
          "wins": 19
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 68,
          "capped_draws": 5,
          "coverage_status": "rated",
          "distinct_rated_opponents": 32,
          "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": "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": 68,
          "raw_elo_rating": 1453.3589845100641,
          "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": 33.0378996400634,
          "uncertainty": 16.4429265428846,
          "unilateral_faults": 0,
          "wins": 14
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 54,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 27,
          "draws": 31,
          "evaluated_setting_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": 54,
          "raw_elo_rating": 1470.7197466096768,
          "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": 34.804158602993404,
          "uncertainty": 23.66998624632421,
          "unilateral_faults": 0,
          "wins": 11
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 58,
          "capped_draws": 4,
          "coverage_status": "rated",
          "distinct_rated_opponents": 29,
          "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": 20,
          "model": "z-ai/glm-5.2",
          "point_rating_method": "sequential_elo",
          "public_id": "E-583be34ca1fb2631",
          "rated_matches": 58,
          "raw_elo_rating": 1513.2067256039966,
          "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": 41.56883825039476,
          "uncertainty": 21.344455490411935,
          "unilateral_faults": 0,
          "wins": 12
        }
      ],
      "GB2-04": [
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 76,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 38,
          "draws": 48,
          "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": 76,
          "raw_elo_rating": 1552.8865414749796,
          "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": 42.16676257859201,
          "uncertainty": 13.230288229818967,
          "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": 1490.9532680536443,
          "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": 31.313916897298004,
          "uncertainty": 10.482614454664043,
          "unilateral_faults": 0,
          "wins": 9
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 98,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 49,
          "draws": 54,
          "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": 98,
          "raw_elo_rating": 1504.8242989260918,
          "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": 34.41262761914292,
          "uncertainty": 6.501890762960602,
          "unilateral_faults": 0,
          "wins": 17
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 100,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 50,
          "draws": 25,
          "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": 100,
          "raw_elo_rating": 1600.0996631851501,
          "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": 51.79519895770521,
          "uncertainty": 6.001859510499461,
          "unilateral_faults": 0,
          "wins": 46
        },
        {
          "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": 1376.1312280226116,
          "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": 9.943666245746922,
          "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": "low",
          "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": 20,
          "capped_draws": 0,
          "coverage_status": "under_covered",
          "distinct_rated_opponents": 10,
          "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": "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-6a79049fd9ab6f5d",
          "rated_matches": 20,
          "raw_elo_rating": 1526.6735769833929,
          "reasoning": "minimal",
          "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": 29.82761442249626,
          "uncertainty": 65.3589451179962,
          "unilateral_faults": 0,
          "wins": 4
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 18,
          "capped_draws": 0,
          "coverage_status": "under_covered",
          "distinct_rated_opponents": 9,
          "draws": 10,
          "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": 4,
          "model": "google/gemini-3.5-flash-lite",
          "point_rating_method": "sequential_elo",
          "public_id": "E-b05b0185d0e8dc2a",
          "rated_matches": 18,
          "raw_elo_rating": 1493.8451062756994,
          "reasoning": "minimal",
          "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": 23.049464206984855,
          "uncertainty": 70.95786693528086,
          "unilateral_faults": 0,
          "wins": 4
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 20,
          "capped_draws": 0,
          "coverage_status": "under_covered",
          "distinct_rated_opponents": 10,
          "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": "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": 1,
          "model": "google/gemini-3.6-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-0b528ba96380a3b5",
          "rated_matches": 20,
          "raw_elo_rating": 1500.744166605296,
          "reasoning": "minimal",
          "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": 25.11668688778358,
          "uncertainty": 65.3589451179962,
          "unilateral_faults": 0,
          "wins": 2
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 24,
          "capped_draws": 0,
          "coverage_status": "under_covered",
          "distinct_rated_opponents": 12,
          "draws": 19,
          "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": 4,
          "model": "google/gemini-3.6-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-846809faa1345207",
          "rated_matches": 24,
          "raw_elo_rating": 1470.2178477461143,
          "reasoning": "minimal",
          "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": 20.89453103634271,
          "uncertainty": 56.25,
          "unilateral_faults": 0,
          "wins": 1
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 86,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 42,
          "draws": 67,
          "evaluated_setting_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": 86,
          "raw_elo_rating": 1491.3691141009099,
          "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": 31.480599265900732,
          "uncertainty": 9.855626741889738,
          "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": 1469.2709415655665,
          "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": 27.37461139902881,
          "uncertainty": 10.482614454664043,
          "unilateral_faults": 0,
          "wins": 4
        },
        {
          "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": "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": 88,
          "raw_elo_rating": 1489.5133398135404,
          "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": 31.231477991886752,
          "uncertainty": 9.249894000318006,
          "unilateral_faults": 0,
          "wins": 11
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 88,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 43,
          "draws": 57,
          "evaluated_setting_identity": {
            "canonical_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": 15,
          "model": "gpt-5.4-mini",
          "point_rating_method": "sequential_elo",
          "public_id": "E-0880cdf1a43cb90c",
          "rated_matches": 88,
          "raw_elo_rating": 1470.7557500321805,
          "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": 27.82354680882762,
          "uncertainty": 9.249894000318006,
          "unilateral_faults": 0,
          "wins": 16
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 94,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 46,
          "draws": 64,
          "evaluated_setting_identity": {
            "canonical_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": 94,
          "raw_elo_rating": 1490.875178692428,
          "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": 31.726131179809055,
          "uncertainty": 7.54891760425771,
          "unilateral_faults": 0,
          "wins": 12
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 86,
          "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-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": 86,
          "raw_elo_rating": 1483.0322829267293,
          "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": 29.965940546014295,
          "uncertainty": 9.855626741889738,
          "unilateral_faults": 0,
          "wins": 7
        },
        {
          "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": 1509.0423085525442,
          "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": 34.50597954900976,
          "uncertainty": 11.132129994845172,
          "unilateral_faults": 0,
          "wins": 13
        },
        {
          "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-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": 86,
          "raw_elo_rating": 1523.1627836273447,
          "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": 37.25696174455382,
          "uncertainty": 9.855626741889738,
          "unilateral_faults": 0,
          "wins": 8
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 114,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 47,
          "draws": 101,
          "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": 6,
          "model": "inclusionai/ling-3.0-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-f38039bb8cc277a1",
          "rated_matches": 114,
          "raw_elo_rating": 1496.113459457968,
          "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": 33.35713798385482,
          "uncertainty": 2.875240412015687,
          "unilateral_faults": 0,
          "wins": 7
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 98,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 49,
          "draws": 54,
          "evaluated_setting_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": 22,
          "model": "meituan/longcat-2.0",
          "point_rating_method": "sequential_elo",
          "public_id": "E-9e1d4bf411e97fa6",
          "rated_matches": 98,
          "raw_elo_rating": 1586.3561576652844,
          "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": 49.225562918867894,
          "uncertainty": 6.501890762960602,
          "unilateral_faults": 0,
          "wins": 22
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 32,
          "capped_draws": 0,
          "coverage_status": "under_covered",
          "distinct_rated_opponents": 16,
          "draws": 17,
          "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": 4,
          "model": "moonshotai/kimi-k3",
          "point_rating_method": "sequential_elo",
          "public_id": "E-3c06949f23d4a77f",
          "rated_matches": 32,
          "raw_elo_rating": 1562.2866801608545,
          "reasoning": "low",
          "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": 39.50571055811572,
          "uncertainty": 43.288827977848925,
          "unilateral_faults": 0,
          "wins": 11
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 94,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 46,
          "draws": 81,
          "evaluated_setting_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": 94,
          "raw_elo_rating": 1475.0635006450743,
          "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": 28.853421449925953,
          "uncertainty": 7.54891760425771,
          "unilateral_faults": 0,
          "wins": 5
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 60,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 30,
          "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": "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": 60,
          "raw_elo_rating": 1504.4747006526225,
          "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": 32.34819561268509,
          "uncertainty": 20.268439966447993,
          "unilateral_faults": 0,
          "wins": 7
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 34,
          "capped_draws": 0,
          "coverage_status": "under_covered",
          "distinct_rated_opponents": 17,
          "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": "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": 14,
          "model": "openai/gpt-oss-120b",
          "point_rating_method": "sequential_elo",
          "public_id": "E-f6de1ce39e48807c",
          "rated_matches": 34,
          "raw_elo_rating": 1394.8462834549794,
          "reasoning": "low",
          "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": 9.451439719406691,
          "uncertainty": 40.76542547285167,
          "unilateral_faults": 0,
          "wins": 2
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 70,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 34,
          "draws": 57,
          "evaluated_setting_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": 70,
          "raw_elo_rating": 1474.1281441770377,
          "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": 27.51487556975524,
          "uncertainty": 15.58908290969266,
          "unilateral_faults": 0,
          "wins": 5
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 70,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 35,
          "draws": 42,
          "evaluated_setting_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": 70,
          "raw_elo_rating": 1509.5599956004069,
          "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": 33.952233073927275,
          "uncertainty": 15.58908290969266,
          "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": 1450.017819843153,
          "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": 23.96778089192692,
          "uncertainty": 9.855626741889738,
          "unilateral_faults": 0,
          "wins": 18
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 90,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 44,
          "draws": 75,
          "evaluated_setting_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": 90,
          "raw_elo_rating": 1496.175509699153,
          "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": 32.527001915886224,
          "uncertainty": 8.664241836095918,
          "unilateral_faults": 0,
          "wins": 4
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 28,
          "capped_draws": 0,
          "coverage_status": "under_covered",
          "distinct_rated_opponents": 14,
          "draws": 22,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "low",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "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": 3,
          "model": "x-ai/grok-4.5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-5a4033db1131bf1d",
          "rated_matches": 28,
          "raw_elo_rating": 1486.528573612316,
          "reasoning": "low",
          "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": 24.897473493704123,
          "uncertainty": 49.09766908852594,
          "unilateral_faults": 0,
          "wins": 3
        },
        {
          "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": 1509.679130642027,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "repaired",
          "score": 34.207021350202915,
          "uncertainty": 13.985026918962571,
          "unilateral_faults": 0,
          "wins": 18
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 66,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 33,
          "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": "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-d58c55e107783a21",
          "rated_matches": 66,
          "raw_elo_rating": 1474.7299039452644,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "repaired",
          "score": 27.370482875885422,
          "uncertainty": 17.33472217815261,
          "unilateral_faults": 0,
          "wins": 3
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 68,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 34,
          "draws": 49,
          "evaluated_setting_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": 68,
          "raw_elo_rating": 1531.2317511480408,
          "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": 37.76551506173829,
          "uncertainty": 16.4429265428846,
          "unilateral_faults": 0,
          "wins": 9
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 80,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 40,
          "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": "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": 80,
          "raw_elo_rating": 1472.1974048811812,
          "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": 27.714014908685787,
          "uncertainty": 11.805555555555554,
          "unilateral_faults": 0,
          "wins": 15
        }
      ],
      "GB2-05": [
        {
          "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": "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": 38,
          "model": "claude-opus-4-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-934b5bc34a7e20b9",
          "rated_matches": 104,
          "raw_elo_rating": 1592.219415390376,
          "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": 51.16554962876789,
          "uncertainty": 5.045003647426665,
          "unilateral_faults": 0,
          "wins": 66
        },
        {
          "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": 54,
          "model": "claude-opus-4-8",
          "point_rating_method": "sequential_elo",
          "public_id": "E-233f9cae6335e53d",
          "rated_matches": 96,
          "raw_elo_rating": 1426.0141768671742,
          "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": 35.33051290926278,
          "uncertainty": 7.017308256680951,
          "unilateral_faults": 0,
          "wins": 42
        },
        {
          "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": "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": 116,
          "raw_elo_rating": 1985.5251096920047,
          "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": 88.47900640476404,
          "uncertainty": 2.4750163521024238,
          "unilateral_faults": 0,
          "wins": 104
        },
        {
          "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": 12,
          "model": "claude-opus-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-b53cb955b1d8baab",
          "rated_matches": 114,
          "raw_elo_rating": 1944.6811591254987,
          "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": 84.59401693770991,
          "uncertainty": 2.875240412015687,
          "unilateral_faults": 0,
          "wins": 102
        },
        {
          "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": "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": 112,
          "raw_elo_rating": 1424.9492077155455,
          "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": 35.51172275800236,
          "uncertainty": 3.286043419179858,
          "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": "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": 96,
          "raw_elo_rating": 1431.2181246632692,
          "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": 35.82165124902767,
          "uncertainty": 7.017308256680951,
          "unilateral_faults": 0,
          "wins": 46
        },
        {
          "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": "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": 57,
          "model": "google/gemini-3.1-flash-lite",
          "point_rating_method": "sequential_elo",
          "public_id": "E-d979b43c3aeea657",
          "rated_matches": 76,
          "raw_elo_rating": 1199.66391873774,
          "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": 13.498926473385124,
          "uncertainty": 13.230288229818967,
          "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": "low",
          "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": 24,
          "capped_draws": 0,
          "coverage_status": "under_covered",
          "distinct_rated_opponents": 11,
          "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": 16,
          "model": "google/gemini-3.5-flash-lite",
          "point_rating_method": "sequential_elo",
          "public_id": "E-214f636367cbdac4",
          "rated_matches": 22,
          "raw_elo_rating": 1353.8369912736307,
          "reasoning": "minimal",
          "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": 24.47995533731953,
          "uncertainty": 60.5072070285374,
          "unilateral_faults": 0,
          "wins": 6
        },
        {
          "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": "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": 18,
          "model": "google/gemini-3.5-flash-lite",
          "point_rating_method": "sequential_elo",
          "public_id": "E-a870d09d3e1a40d4",
          "rated_matches": 22,
          "raw_elo_rating": 1296.1615294294538,
          "reasoning": "minimal",
          "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": 19.036658885234043,
          "uncertainty": 60.5072070285374,
          "unilateral_faults": 0,
          "wins": 4
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 20,
          "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": "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-9bef179ce22a6c93",
          "rated_matches": 20,
          "raw_elo_rating": 1586.7104366140052,
          "reasoning": "minimal",
          "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": 46.09177429753464,
          "uncertainty": 65.3589451179962,
          "unilateral_faults": 0,
          "wins": 13
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 40,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 20,
          "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": 11,
          "model": "google/gemini-3.6-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-e23af86eb5787555",
          "rated_matches": 40,
          "raw_elo_rating": 1691.6033408260928,
          "reasoning": "minimal",
          "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": 58.33360096442092,
          "uncertainty": 34.33688094430304,
          "unilateral_faults": 0,
          "wins": 29
        },
        {
          "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": 1206.244527485814,
          "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": 14.548948613994082,
          "uncertainty": 7.54891760425771,
          "unilateral_faults": 0,
          "wins": 27
        },
        {
          "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-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": 64,
          "model": "gpt-4.1",
          "point_rating_method": "sequential_elo",
          "public_id": "E-1b9f1f7b70f02927",
          "rated_matches": 92,
          "raw_elo_rating": 1184.8550619458447,
          "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": 12.488827301220297,
          "uncertainty": 8.09758473652126,
          "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": "low",
          "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": 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",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_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": 90,
          "raw_elo_rating": 1777.5579433554326,
          "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": 68.38417347397768,
          "uncertainty": 8.664241836095918,
          "unilateral_faults": 0,
          "wins": 65
        },
        {
          "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-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": 64,
          "model": "gpt-5.4-mini",
          "point_rating_method": "sequential_elo",
          "public_id": "E-427bdffeacc6c394",
          "rated_matches": 92,
          "raw_elo_rating": 1348.5279664398565,
          "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": 27.935953546031328,
          "uncertainty": 8.09758473652126,
          "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": 1261.571795536862,
          "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": 19.642199321792404,
          "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": 1211.7757764699222,
          "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": 14.986767312208398,
          "uncertainty": 8.664241836095918,
          "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-5.5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_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-5.5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-6f42dbbf02274b56",
          "rated_matches": 90,
          "raw_elo_rating": 1553.2854909074172,
          "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": 47.21778129130201,
          "uncertainty": 8.664241836095918,
          "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": 1059.7162217483137,
          "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": 0.5457336893360095,
          "uncertainty": 9.855626741889738,
          "unilateral_faults": 2,
          "wins": 7
        },
        {
          "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": 1662.6720777987493,
          "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": 57.70473458705692,
          "uncertainty": 6.501890762960602,
          "unilateral_faults": 0,
          "wins": 59
        },
        {
          "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-5.6-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": 35,
          "model": "gpt-5.6-terra",
          "point_rating_method": "sequential_elo",
          "public_id": "E-1f00b423eab1c19d",
          "rated_matches": 88,
          "raw_elo_rating": 1578.1507673596157,
          "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": 49.52029893343254,
          "uncertainty": 9.249894000318006,
          "unilateral_faults": 0,
          "wins": 53
        },
        {
          "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": "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": 69,
          "model": "meituan/longcat-2.0",
          "point_rating_method": "sequential_elo",
          "public_id": "E-067ab716d64e3e9a",
          "rated_matches": 90,
          "raw_elo_rating": 1171.0008029797596,
          "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": 11.1385056522926,
          "uncertainty": 8.664241836095918,
          "unilateral_faults": 2,
          "wins": 21
        },
        {
          "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": "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": 57,
          "model": "meituan/longcat-2.0",
          "point_rating_method": "sequential_elo",
          "public_id": "E-8cc657b7db4428cb",
          "rated_matches": 84,
          "raw_elo_rating": 1225.2854224221107,
          "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": 16.124489539369485,
          "uncertainty": 10.482614454664043,
          "unilateral_faults": 2,
          "wins": 27
        },
        {
          "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": "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": 112,
          "raw_elo_rating": 1469.2367408862915,
          "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": 39.69149287984802,
          "uncertainty": 3.286043419179858,
          "unilateral_faults": 0,
          "wins": 54
        },
        {
          "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": "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": 96,
          "raw_elo_rating": 1391.2176833271508,
          "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": 32.0464884077659,
          "uncertainty": 7.017308256680951,
          "unilateral_faults": 0,
          "wins": 44
        },
        {
          "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": "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": 12,
          "model": "moonshotai/kimi-k3",
          "point_rating_method": "sequential_elo",
          "public_id": "E-4419230379dcd41e",
          "rated_matches": 52,
          "raw_elo_rating": 1712.1885468405728,
          "reasoning": "low",
          "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": 60.98661317118852,
          "uncertainty": 24.930281974344517,
          "unilateral_faults": 0,
          "wins": 40
        },
        {
          "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": "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": 52,
          "model": "nex-agi/nex-n2-pro",
          "point_rating_method": "sequential_elo",
          "public_id": "E-962a9da8812a74d4",
          "rated_matches": 104,
          "raw_elo_rating": 1500.9159982859114,
          "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": 42.54851301568021,
          "uncertainty": 5.045003647426665,
          "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": "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": 86,
          "raw_elo_rating": 1597.6892957530818,
          "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": 51.31857245670056,
          "uncertainty": 9.855626741889738,
          "unilateral_faults": 0,
          "wins": 53
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 56,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 28,
          "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": 35,
          "model": "openai/gpt-oss-120b",
          "point_rating_method": "sequential_elo",
          "public_id": "E-172336d3fd38632a",
          "rated_matches": 56,
          "raw_elo_rating": 1401.6386697045618,
          "reasoning": "low",
          "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": 31.862785225358834,
          "uncertainty": 22.47661785325219,
          "unilateral_faults": 0,
          "wins": 21
        },
        {
          "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": "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": 100,
          "raw_elo_rating": 1810.8806685198024,
          "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": 71.7301229385181,
          "uncertainty": 6.001859510499461,
          "unilateral_faults": 0,
          "wins": 76
        },
        {
          "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": "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": 46,
          "model": "poolside/laguna-s-2.1",
          "point_rating_method": "sequential_elo",
          "public_id": "E-21623e96b2b104e9",
          "rated_matches": 92,
          "raw_elo_rating": 1407.0390256107005,
          "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": 33.458112027447555,
          "uncertainty": 8.09758473652126,
          "unilateral_faults": 0,
          "wins": 46
        },
        {
          "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": "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": 52,
          "model": "qwen/qwen3.7-max",
          "point_rating_method": "sequential_elo",
          "public_id": "E-c577c41440c17864",
          "rated_matches": 104,
          "raw_elo_rating": 1525.3995628419666,
          "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": 44.85922359902054,
          "uncertainty": 5.045003647426665,
          "unilateral_faults": 0,
          "wins": 52
        },
        {
          "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": "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": 52,
          "model": "qwen/qwen3.7-plus",
          "point_rating_method": "sequential_elo",
          "public_id": "E-94daaf1196d89c6c",
          "rated_matches": 100,
          "raw_elo_rating": 1504.6944028280163,
          "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": 42.83286645498502,
          "uncertainty": 6.001859510499461,
          "unilateral_faults": 0,
          "wins": 48
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 30,
          "capped_draws": 0,
          "coverage_status": "under_covered",
          "distinct_rated_opponents": 13,
          "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": 15,
          "model": "stepfun/step-3.7-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-50f22f1c15a8fd4a",
          "rated_matches": 26,
          "raw_elo_rating": 1435.5757190524112,
          "reasoning": "low",
          "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": 32.800743128476654,
          "uncertainty": 52.475044864937615,
          "unilateral_faults": 0,
          "wins": 11
        },
        {
          "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": "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": 102,
          "raw_elo_rating": 1379.0311903903728,
          "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": 31.009668601208,
          "uncertainty": 5.516463908214657,
          "unilateral_faults": 0,
          "wins": 39
        },
        {
          "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": "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": 68,
          "model": "thinkingmachines/inkling",
          "point_rating_method": "sequential_elo",
          "public_id": "E-0f05573125dedc2b",
          "rated_matches": 102,
          "raw_elo_rating": 1350.745875849399,
          "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": 28.340156344800302,
          "uncertainty": 5.516463908214657,
          "unilateral_faults": 0,
          "wins": 34
        },
        {
          "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": "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": 71,
          "model": "thinkingmachines/inkling",
          "point_rating_method": "sequential_elo",
          "public_id": "E-f7a1d86c7e241f8d",
          "rated_matches": 108,
          "raw_elo_rating": 1358.0512100543676,
          "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": 29.133446524932413,
          "uncertainty": 4.1413142610575715,
          "unilateral_faults": 0,
          "wins": 37
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 48,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 24,
          "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": 18,
          "model": "x-ai/grok-4.5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-3c5879def34f7d38",
          "rated_matches": 48,
          "raw_elo_rating": 1611.4942172905676,
          "reasoning": "low",
          "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": 51.27577822917729,
          "uncertainty": 27.678571428571434,
          "unilateral_faults": 0,
          "wins": 30
        },
        {
          "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": 1644.3935809032257,
          "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": 55.72643086868543,
          "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": 1344.3523439503517,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "repaired",
          "score": 27.409130090108036,
          "uncertainty": 9.855626741889738,
          "unilateral_faults": 0,
          "wins": 32
        },
        {
          "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": 43,
          "model": "xiaomi/mimo-v2.5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-be8fc9653466bbe1",
          "rated_matches": 82,
          "raw_elo_rating": 1426.0236645885172,
          "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": 35.02072932706977,
          "uncertainty": 11.132129994845172,
          "unilateral_faults": 0,
          "wins": 39
        },
        {
          "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": "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": 96,
          "raw_elo_rating": 1450.2800289578179,
          "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": 37.62067621907194,
          "uncertainty": 7.017308256680951,
          "unilateral_faults": 0,
          "wins": 50
        },
        {
          "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": "2026-07-11T14:00:45Z",
          "losses": 40,
          "model": "z-ai/glm-5.2",
          "point_rating_method": "sequential_elo",
          "public_id": "E-38e323f4ce233fa1",
          "rated_matches": 82,
          "raw_elo_rating": 1431.1307416928755,
          "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": 35.50272520181086,
          "uncertainty": 11.132129994845172,
          "unilateral_faults": 0,
          "wins": 42
        },
        {
          "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": "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": 80,
          "raw_elo_rating": 1624.840786681568,
          "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": 53.73385232288734,
          "uncertainty": 11.805555555555554,
          "unilateral_faults": 0,
          "wins": 38
        }
      ],
      "GB2-06": [
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 92,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 46,
          "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": 40,
          "model": "claude-opus-4-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-40a259ca8a40b5b4",
          "rated_matches": 92,
          "raw_elo_rating": 1474.2036667060856,
          "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": 51.13788519283952,
          "uncertainty": 8.09758473652126,
          "unilateral_faults": 0,
          "wins": 47
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 88,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 44,
          "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": 29,
          "model": "claude-opus-4-8",
          "point_rating_method": "sequential_elo",
          "public_id": "E-db414178442322d3",
          "rated_matches": 88,
          "raw_elo_rating": 1583.0538051265532,
          "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": 62.619735110933746,
          "uncertainty": 9.249894000318006,
          "unilateral_faults": 0,
          "wins": 50
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 100,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 50,
          "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": 100,
          "raw_elo_rating": 1924.0542264240664,
          "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": 99.17317608622864,
          "uncertainty": 6.001859510499461,
          "unilateral_faults": 0,
          "wins": 84
        },
        {
          "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": 1177.8349760515114,
          "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": 19.56075363575773,
          "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": 1642.2089240234834,
          "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": 68.86134465387879,
          "uncertainty": 9.855626741889738,
          "unilateral_faults": 0,
          "wins": 54
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 78,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 39,
          "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": 34,
          "model": "google/gemini-3.1-flash-lite",
          "point_rating_method": "sequential_elo",
          "public_id": "E-dc1c0f46738d1091",
          "rated_matches": 78,
          "raw_elo_rating": 1432.4590360383802,
          "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": 46.321870346065246,
          "uncertainty": 12.5043950463012,
          "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": "low",
          "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": 24,
          "capped_draws": 0,
          "coverage_status": "under_covered",
          "distinct_rated_opponents": 12,
          "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": 10,
          "model": "google/gemini-3.5-flash-lite",
          "point_rating_method": "sequential_elo",
          "public_id": "E-3efea50fdbbd1829",
          "rated_matches": 24,
          "raw_elo_rating": 1621.018317341208,
          "reasoning": "minimal",
          "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": 62.65850437935162,
          "uncertainty": 56.25,
          "unilateral_faults": 0,
          "wins": 14
        },
        {
          "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": "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": 6,
          "model": "google/gemini-3.5-flash-lite",
          "point_rating_method": "sequential_elo",
          "public_id": "E-46f1468c28505bfe",
          "rated_matches": 22,
          "raw_elo_rating": 1669.4100232838757,
          "reasoning": "minimal",
          "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": 67.44429140836692,
          "uncertainty": 60.5072070285374,
          "unilateral_faults": 0,
          "wins": 16
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 34,
          "capped_draws": 0,
          "coverage_status": "under_covered",
          "distinct_rated_opponents": 17,
          "draws": 8,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "minimal",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "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-5455742d003ec402",
          "rated_matches": 34,
          "raw_elo_rating": 1466.9183145223224,
          "reasoning": "minimal",
          "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": 47.58256978506472,
          "uncertainty": 40.76542547285167,
          "unilateral_faults": 0,
          "wins": 13
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 24,
          "capped_draws": 0,
          "coverage_status": "under_covered",
          "distinct_rated_opponents": 12,
          "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": "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-bb2e288b40b1a588",
          "rated_matches": 24,
          "raw_elo_rating": 1440.9596297120831,
          "reasoning": "minimal",
          "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": 43.503129931460265,
          "uncertainty": 56.25,
          "unilateral_faults": 0,
          "wins": 11
        },
        {
          "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": 1373.38682774224,
          "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": 40.63225251749573,
          "uncertainty": 5.516463908214657,
          "unilateral_faults": 0,
          "wins": 41
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 88,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 44,
          "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": 34,
          "model": "gpt-4.1",
          "point_rating_method": "sequential_elo",
          "public_id": "E-4dcd6d3653c67437",
          "rated_matches": 88,
          "raw_elo_rating": 1564.774398115172,
          "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": 60.675097556373565,
          "uncertainty": 9.249894000318006,
          "unilateral_faults": 0,
          "wins": 44
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 82,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 41,
          "draws": 8,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.4",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 22,
          "model": "gpt-5.4",
          "point_rating_method": "sequential_elo",
          "public_id": "E-00a57c19a4229948",
          "rated_matches": 82,
          "raw_elo_rating": 1677.2495360528883,
          "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": 72.48046758902608,
          "uncertainty": 11.132129994845172,
          "unilateral_faults": 0,
          "wins": 52
        },
        {
          "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": 1365.4665711563578,
          "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": 39.705796487312476,
          "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": 1397.925943025314,
          "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": 43.20151257567426,
          "uncertainty": 6.001859510499461,
          "unilateral_faults": 0,
          "wins": 45
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 94,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 47,
          "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": 94,
          "raw_elo_rating": 1619.4900816896625,
          "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": 66.64073960908615,
          "uncertainty": 7.54891760425771,
          "unilateral_faults": 0,
          "wins": 62
        },
        {
          "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": 1036.920602437529,
          "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": 4.569710286459858,
          "uncertainty": 8.664241836095918,
          "unilateral_faults": 0,
          "wins": 9
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 98,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 48,
          "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": 57,
          "model": "gpt-5.6-sol",
          "point_rating_method": "sequential_elo",
          "public_id": "E-992b9a5ebbb74c80",
          "rated_matches": 98,
          "raw_elo_rating": 1417.4757599964255,
          "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": 45.23874521686571,
          "uncertainty": 6.501890762960602,
          "unilateral_faults": 0,
          "wins": 38
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 100,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 49,
          "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": 51,
          "model": "gpt-5.6-terra",
          "point_rating_method": "sequential_elo",
          "public_id": "E-22ffdca36d9bac9c",
          "rated_matches": 100,
          "raw_elo_rating": 1426.7393326842414,
          "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": 46.266797985099174,
          "uncertainty": 6.001859510499461,
          "unilateral_faults": 0,
          "wins": 47
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 130,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 53,
          "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": 1352.898251283575,
          "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": 38.92760032113381,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 56
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 128,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 50,
          "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": 987.2524056144644,
          "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": 114,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 55,
          "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": 61,
          "model": "meituan/longcat-2.0",
          "point_rating_method": "sequential_elo",
          "public_id": "E-3e8b2d11481a50d7",
          "rated_matches": 114,
          "raw_elo_rating": 1422.3546000074646,
          "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": 46.06643026564779,
          "uncertainty": 2.875240412015687,
          "unilateral_faults": 0,
          "wins": 47
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 94,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 47,
          "draws": 11,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "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": 42,
          "model": "meituan/longcat-2.0",
          "point_rating_method": "sequential_elo",
          "public_id": "E-e3023ff7ecf82fc4",
          "rated_matches": 94,
          "raw_elo_rating": 1534.1588146752608,
          "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": 57.56285287506405,
          "uncertainty": 7.54891760425771,
          "unilateral_faults": 0,
          "wins": 41
        },
        {
          "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": 1378.8243454602684,
          "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": 40.942819015465346,
          "uncertainty": 8.664241836095918,
          "unilateral_faults": 0,
          "wins": 35
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 48,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 24,
          "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": "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": 15,
          "model": "moonshotai/kimi-k3",
          "point_rating_method": "sequential_elo",
          "public_id": "E-95a5c0e17cd4b70a",
          "rated_matches": 48,
          "raw_elo_rating": 1593.6276146432358,
          "reasoning": "low",
          "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": 62.17620587170125,
          "uncertainty": 27.678571428571434,
          "unilateral_faults": 0,
          "wins": 31
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 90,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 44,
          "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": 65,
          "model": "nex-agi/nex-n2-pro",
          "point_rating_method": "sequential_elo",
          "public_id": "E-973417dedd770061",
          "rated_matches": 90,
          "raw_elo_rating": 1271.588396713997,
          "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": 29.534623279080066,
          "uncertainty": 8.664241836095918,
          "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": 1295.593141086351,
          "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": 31.82099690512065,
          "uncertainty": 11.805555555555554,
          "unilateral_faults": 0,
          "wins": 31
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 46,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 23,
          "draws": 12,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "low",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "o3",
            "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-21T14:20:15Z",
          "losses": 21,
          "model": "o3",
          "point_rating_method": "sequential_elo",
          "public_id": "E-9f2773793ec1d7e3",
          "rated_matches": 46,
          "raw_elo_rating": 1386.3188740171406,
          "reasoning": "low",
          "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": 39.99386525596274,
          "uncertainty": 29.182495748947275,
          "unilateral_faults": 0,
          "wins": 13
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 60,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 30,
          "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": 32,
          "model": "openai/gpt-oss-120b",
          "point_rating_method": "sequential_elo",
          "public_id": "E-b75de88bfc62ab22",
          "rated_matches": 60,
          "raw_elo_rating": 1489.7264897089944,
          "reasoning": "low",
          "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": 51.753438139182734,
          "uncertainty": 20.268439966447993,
          "unilateral_faults": 0,
          "wins": 28
        },
        {
          "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": 1270.3210113293824,
          "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": 29.784727597962565,
          "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": 1279.3223943837968,
          "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": 30.541429111812185,
          "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": 1276.4806787457837,
          "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": 30.26055359128659,
          "uncertainty": 6.25,
          "unilateral_faults": 0,
          "wins": 26
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 46,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 23,
          "draws": 3,
          "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": 14,
          "model": "stepfun/step-3.7-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-ab4ccc8ca01bc627",
          "rated_matches": 46,
          "raw_elo_rating": 1623.016874040932,
          "reasoning": "low",
          "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": 65.17475978109492,
          "uncertainty": 29.182495748947275,
          "unilateral_faults": 0,
          "wins": 29
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 110,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 53,
          "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": 56,
          "model": "thinkingmachines/inkling",
          "point_rating_method": "sequential_elo",
          "public_id": "E-02be9616e86c7055",
          "rated_matches": 110,
          "raw_elo_rating": 1364.1456650071532,
          "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": 39.80306201224402,
          "uncertainty": 3.707899787624953,
          "unilateral_faults": 0,
          "wins": 53
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 42,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 21,
          "draws": 7,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "low",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "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": 12,
          "model": "x-ai/grok-4.5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-8dbfeb56f012d9c6",
          "rated_matches": 42,
          "raw_elo_rating": 1579.5168804285463,
          "reasoning": "low",
          "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": 60.26477097483131,
          "uncertainty": 32.49928516630233,
          "unilateral_faults": 0,
          "wins": 23
        },
        {
          "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": 1370.0835377541052,
          "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": 40.23952442879587,
          "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": 1398.3402844497405,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "repaired",
          "score": 42.80896869171179,
          "uncertainty": 11.132129994845172,
          "unilateral_faults": 0,
          "wins": 34
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 84,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 42,
          "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": 84,
          "raw_elo_rating": 1630.4513120878032,
          "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": 67.55716094653901,
          "uncertainty": 10.482614454664043,
          "unilateral_faults": 0,
          "wins": 51
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 100,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 50,
          "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": 44,
          "model": "xiaomi/mimo-v2.5-pro",
          "point_rating_method": "sequential_elo",
          "public_id": "E-6b662c734cdcff91",
          "rated_matches": 100,
          "raw_elo_rating": 1441.8800041097018,
          "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": 47.87752410093403,
          "uncertainty": 6.001859510499461,
          "unilateral_faults": 0,
          "wins": 55
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 74,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 37,
          "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": 29,
          "model": "z-ai/glm-5.2",
          "point_rating_method": "sequential_elo",
          "public_id": "E-657c61c9039ce566",
          "rated_matches": 74,
          "raw_elo_rating": 1525.1488052535287,
          "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": 56.05657192326941,
          "uncertainty": 13.985026918962571,
          "unilateral_faults": 0,
          "wins": 35
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 70,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 35,
          "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": 70,
          "raw_elo_rating": 1681.9707996856102,
          "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": 72.60341578696683,
          "uncertainty": 15.58908290969266,
          "unilateral_faults": 0,
          "wins": 31
        }
      ],
      "GB2-07": [
        {
          "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": "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": 51,
          "model": "claude-opus-4-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-ca22621c58b6f244",
          "rated_matches": 108,
          "raw_elo_rating": 1532.1958341337388,
          "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": 49.231533682902075,
          "uncertainty": 4.1413142610575715,
          "unilateral_faults": 0,
          "wins": 57
        },
        {
          "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": "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": 35,
          "model": "claude-opus-4-8",
          "point_rating_method": "sequential_elo",
          "public_id": "E-76804598cce96e62",
          "rated_matches": 92,
          "raw_elo_rating": 1576.1603536781683,
          "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": 53.294481025847816,
          "uncertainty": 8.09758473652126,
          "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-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": 96,
          "raw_elo_rating": 1835.2604164135125,
          "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": 79.18257070094032,
          "uncertainty": 7.017308256680951,
          "unilateral_faults": 0,
          "wins": 74
        },
        {
          "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": 1477.8028209416357,
          "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": 43.66667703715262,
          "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": 1126.4180876957776,
          "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": 8.462538450612445,
          "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": 1406.6667442109426,
          "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": 36.22574841026145,
          "uncertainty": 10.482614454664043,
          "unilateral_faults": 0,
          "wins": 36
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 98,
          "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": "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": 42,
          "model": "deepseek/deepseek-v4-pro",
          "point_rating_method": "sequential_elo",
          "public_id": "E-f76d96b0f3163d4b",
          "rated_matches": 98,
          "raw_elo_rating": 1486.6131615979011,
          "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": 44.504203648777164,
          "uncertainty": 6.501890762960602,
          "unilateral_faults": 0,
          "wins": 56
        },
        {
          "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": 1045.6951836273022,
          "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": "low",
          "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": 20,
          "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": "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": 14,
          "model": "google/gemini-3.5-flash-lite",
          "point_rating_method": "sequential_elo",
          "public_id": "E-455ee67905f5f955",
          "rated_matches": 20,
          "raw_elo_rating": 1456.0840723741392,
          "reasoning": "minimal",
          "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": 36.775075900320765,
          "uncertainty": 65.3589451179962,
          "unilateral_faults": 0,
          "wins": 6
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 20,
          "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": "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": 4,
          "model": "google/gemini-3.5-flash-lite",
          "point_rating_method": "sequential_elo",
          "public_id": "E-e2e240babaf0b862",
          "rated_matches": 20,
          "raw_elo_rating": 1676.1076487053144,
          "reasoning": "minimal",
          "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": 58.685739891632934,
          "uncertainty": 65.3589451179962,
          "unilateral_faults": 0,
          "wins": 16
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 26,
          "capped_draws": 0,
          "coverage_status": "under_covered",
          "distinct_rated_opponents": 11,
          "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": 9,
          "model": "google/gemini-3.6-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-8e9b51be911dad38",
          "rated_matches": 22,
          "raw_elo_rating": 1512.9516514437669,
          "reasoning": "minimal",
          "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": 42.82465604818685,
          "uncertainty": 60.5072070285374,
          "unilateral_faults": 0,
          "wins": 13
        },
        {
          "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": "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": 6,
          "model": "google/gemini-3.6-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-a2d90fcdc2f4ef9d",
          "rated_matches": 22,
          "raw_elo_rating": 1638.6834635651658,
          "reasoning": "minimal",
          "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": 55.345439204007334,
          "uncertainty": 60.5072070285374,
          "unilateral_faults": 0,
          "wins": 16
        },
        {
          "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": 1288.3055324602838,
          "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": 24.48890361547792,
          "uncertainty": 9.855626741889738,
          "unilateral_faults": 2,
          "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": "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": 45,
          "model": "gpt-4.1",
          "point_rating_method": "sequential_elo",
          "public_id": "E-fcfa606d3cbb0ba0",
          "rated_matches": 84,
          "raw_elo_rating": 1549.1610657525957,
          "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": 50.41579682248144,
          "uncertainty": 10.482614454664043,
          "unilateral_faults": 0,
          "wins": 39
        },
        {
          "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": "low",
          "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": 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": 1299.2820176175837,
          "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": 25.63023441070387,
          "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": 1144.1874341325886,
          "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": 10.185410895530666,
          "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": 1377.7199812397787,
          "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": 33.70010205201074,
          "uncertainty": 6.001859510499461,
          "unilateral_faults": 0,
          "wins": 38
        },
        {
          "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": "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": 50,
          "model": "gpt-5.5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-4edfe4117ad3e936",
          "rated_matches": 108,
          "raw_elo_rating": 1517.5057890966405,
          "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": 47.768651176435434,
          "uncertainty": 4.1413142610575715,
          "unilateral_faults": 0,
          "wins": 58
        },
        {
          "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": 1172.2216045615141,
          "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": 12.928888178071984,
          "uncertainty": 9.855626741889738,
          "unilateral_faults": 1,
          "wins": 17
        },
        {
          "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-5.6-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-bef852aad169a609",
          "rated_matches": 90,
          "raw_elo_rating": 1667.940513626986,
          "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": 62.3891044858804,
          "uncertainty": 8.664241836095918,
          "unilateral_faults": 0,
          "wins": 52
        },
        {
          "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": "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": 58,
          "model": "gpt-5.6-terra",
          "point_rating_method": "sequential_elo",
          "public_id": "E-8ebe8776c7d44d46",
          "rated_matches": 106,
          "raw_elo_rating": 1445.8694948539608,
          "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": 40.59938350830355,
          "uncertainty": 4.586824452283178,
          "unilateral_faults": 0,
          "wins": 48
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 98,
          "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": "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": 45,
          "model": "meituan/longcat-2.0",
          "point_rating_method": "sequential_elo",
          "public_id": "E-c1f595f47c71e648",
          "rated_matches": 98,
          "raw_elo_rating": 1427.0152922360796,
          "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": 38.56925380404107,
          "uncertainty": 6.501890762960602,
          "unilateral_faults": 0,
          "wins": 53
        },
        {
          "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": "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": 54,
          "model": "meituan/longcat-2.0",
          "point_rating_method": "sequential_elo",
          "public_id": "E-e2db910734ca5315",
          "rated_matches": 104,
          "raw_elo_rating": 1492.5125839523562,
          "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": 45.20775258104111,
          "uncertainty": 5.045003647426665,
          "unilateral_faults": 0,
          "wins": 50
        },
        {
          "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": 1440.0116718921627,
          "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": 39.64455151180685,
          "uncertainty": 9.249894000318006,
          "unilateral_faults": 0,
          "wins": 37
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 48,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 24,
          "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": 26,
          "model": "moonshotai/kimi-k3",
          "point_rating_method": "sequential_elo",
          "public_id": "E-4d8815930b656774",
          "rated_matches": 48,
          "raw_elo_rating": 1436.117544167627,
          "reasoning": "low",
          "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": 37.78861144361751,
          "uncertainty": 27.678571428571434,
          "unilateral_faults": 0,
          "wins": 22
        },
        {
          "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": "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": 92,
          "raw_elo_rating": 1633.70258494576,
          "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": 59.024723737278265,
          "uncertainty": 8.09758473652126,
          "unilateral_faults": 0,
          "wins": 63
        },
        {
          "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": 1179.1916405345034,
          "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": 13.294011760456632,
          "uncertainty": 13.985026918962571,
          "unilateral_faults": 0,
          "wins": 12
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 50,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 25,
          "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
            "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": 25,
          "model": "o3",
          "point_rating_method": "sequential_elo",
          "public_id": "E-585aa996c86c4b8a",
          "rated_matches": 50,
          "raw_elo_rating": 1495.7553944062338,
          "reasoning": "low",
          "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": 43.84023648176475,
          "uncertainty": 26.264004201400486,
          "unilateral_faults": 0,
          "wins": 25
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 48,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 24,
          "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": 35,
          "model": "openai/gpt-oss-120b",
          "point_rating_method": "sequential_elo",
          "public_id": "E-759d747bb732d949",
          "rated_matches": 48,
          "raw_elo_rating": 1294.4125387163276,
          "reasoning": "low",
          "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": 23.677165697198408,
          "uncertainty": 27.678571428571434,
          "unilateral_faults": 0,
          "wins": 13
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 105,
          "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": 59,
          "model": "poolside/laguna-s-2.1",
          "point_rating_method": "sequential_elo",
          "public_id": "E-069a963abdd14cdf",
          "rated_matches": 96,
          "raw_elo_rating": 1482.0506801872393,
          "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": 44.008795335771325,
          "uncertainty": 7.017308256680951,
          "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": "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-d8e68d23876f6d21",
          "rated_matches": 98,
          "raw_elo_rating": 1614.907125088047,
          "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": 57.280134178672675,
          "uncertainty": 6.501890762960602,
          "unilateral_faults": 0,
          "wins": 51
        },
        {
          "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": 1705.0967292013736,
          "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": 66.08924139036272,
          "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": 1131.5762374150424,
          "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": 8.83134021951195,
          "uncertainty": 10.482614454664043,
          "unilateral_faults": 2,
          "wins": 18
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 58,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 29,
          "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": 31,
          "model": "stepfun/step-3.7-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-1140a7c92290e8f4",
          "rated_matches": 58,
          "raw_elo_rating": 1394.0233627026678,
          "reasoning": "low",
          "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": 34.10135332885759,
          "uncertainty": 21.344455490411935,
          "unilateral_faults": 0,
          "wins": 27
        },
        {
          "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": 1364.5064243167951,
          "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": 32.460482495895945,
          "uncertainty": 5.045003647426665,
          "unilateral_faults": 0,
          "wins": 48
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 36,
          "capped_draws": 0,
          "coverage_status": "under_covered",
          "distinct_rated_opponents": 18,
          "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": 8,
          "model": "x-ai/grok-4.5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-1d206565b78f3121",
          "rated_matches": 36,
          "raw_elo_rating": 1739.8022649892123,
          "reasoning": "low",
          "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": 67.17244175325133,
          "uncertainty": 38.449493652678655,
          "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": "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": 1216.326014794011,
          "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": 17.320948925619717,
          "uncertainty": 9.855626741889738,
          "unilateral_faults": 2,
          "wins": 27
        },
        {
          "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": 38,
          "model": "xiaomi/mimo-v2.5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-47d67dcf0077af42",
          "rated_matches": 86,
          "raw_elo_rating": 1553.7177285588737,
          "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": 50.91951412041442,
          "uncertainty": 9.855626741889738,
          "unilateral_faults": 0,
          "wins": 48
        },
        {
          "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": "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": 36,
          "model": "xiaomi/mimo-v2.5-pro",
          "point_rating_method": "sequential_elo",
          "public_id": "E-83580d03385c6759",
          "rated_matches": 92,
          "raw_elo_rating": 1554.93981257272,
          "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": 51.181270461651444,
          "uncertainty": 8.09758473652126,
          "unilateral_faults": 0,
          "wins": 56
        },
        {
          "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": "2026-07-11T14:00:45Z",
          "losses": 41,
          "model": "z-ai/glm-5.2",
          "point_rating_method": "sequential_elo",
          "public_id": "E-62e8714f035ebc68",
          "rated_matches": 70,
          "raw_elo_rating": 1428.1721734848647,
          "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": 37.960514063897726,
          "uncertainty": 15.58908290969266,
          "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": "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": 38,
          "model": "z-ai/glm-5.2",
          "point_rating_method": "sequential_elo",
          "public_id": "E-e31f275ab7ef3741",
          "rated_matches": 76,
          "raw_elo_rating": 1632.9069856979993,
          "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": 58.53659031600019,
          "uncertainty": 13.230288229818967,
          "unilateral_faults": 0,
          "wins": 38
        }
      ],
      "GB2-08": [
        {
          "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": "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": 88,
          "raw_elo_rating": 1781.1633732381583,
          "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": 68.15920342920347,
          "uncertainty": 9.249894000318006,
          "unilateral_faults": 0,
          "wins": 65
        },
        {
          "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": "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": 88,
          "raw_elo_rating": 1767.4200337972638,
          "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": 66.52956277651462,
          "uncertainty": 9.249894000318006,
          "unilateral_faults": 0,
          "wins": 63
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 70,
          "capped_draws": 7,
          "coverage_status": "rated",
          "distinct_rated_opponents": 35,
          "draws": 7,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-opus-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-43cc1c89fa5720b3",
          "rated_matches": 70,
          "raw_elo_rating": 1764.9276140971756,
          "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": 65.63267534378616,
          "uncertainty": 15.58908290969266,
          "unilateral_faults": 0,
          "wins": 51
        },
        {
          "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": "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": 36,
          "model": "claude-opus-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-5a7942274854aaa6",
          "rated_matches": 112,
          "raw_elo_rating": 1636.5767116211482,
          "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": 51.580324918294124,
          "uncertainty": 3.286043419179858,
          "unilateral_faults": 0,
          "wins": 76
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 118,
          "capped_draws": 94,
          "coverage_status": "rated",
          "distinct_rated_opponents": 52,
          "draws": 94,
          "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": 118,
          "raw_elo_rating": 1422.2229879671406,
          "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": 26.27689482403025,
          "uncertainty": 2.084924851410568,
          "unilateral_faults": 0,
          "wins": 4
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 110,
          "capped_draws": 86,
          "coverage_status": "rated",
          "distinct_rated_opponents": 53,
          "draws": 86,
          "evaluated_setting_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": 110,
          "raw_elo_rating": 1424.5465939205094,
          "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": 26.3984628011689,
          "uncertainty": 3.707899787624953,
          "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": 1525.8670668329498,
          "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": 38.37160182164898,
          "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": "low",
          "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": 36,
          "capped_draws": 31,
          "coverage_status": "under_covered",
          "distinct_rated_opponents": 18,
          "draws": 31,
          "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": 4,
          "model": "google/gemini-3.5-flash-lite",
          "point_rating_method": "sequential_elo",
          "public_id": "E-284d554eca16e6f6",
          "rated_matches": 36,
          "raw_elo_rating": 1453.3075258165225,
          "reasoning": "minimal",
          "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": 26.513204409086146,
          "uncertainty": 38.449493652678655,
          "unilateral_faults": 0,
          "wins": 1
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 38,
          "capped_draws": 33,
          "coverage_status": "under_covered",
          "distinct_rated_opponents": 19,
          "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-3.5-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": 4,
          "model": "google/gemini-3.5-flash-lite",
          "point_rating_method": "sequential_elo",
          "public_id": "E-af119b49b8f1d63d",
          "rated_matches": 38,
          "raw_elo_rating": 1455.3639544861342,
          "reasoning": "minimal",
          "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": 26.95961769480189,
          "uncertainty": 36.31407690254356,
          "unilateral_faults": 0,
          "wins": 1
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 38,
          "capped_draws": 33,
          "coverage_status": "under_covered",
          "distinct_rated_opponents": 19,
          "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": 4,
          "model": "google/gemini-3.6-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-657c523bc9e9f80c",
          "rated_matches": 38,
          "raw_elo_rating": 1451.0945398206582,
          "reasoning": "minimal",
          "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": 26.45336433971537,
          "uncertainty": 36.31407690254356,
          "unilateral_faults": 0,
          "wins": 1
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 44,
          "capped_draws": 37,
          "coverage_status": "rated",
          "distinct_rated_opponents": 22,
          "draws": 37,
          "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": 6,
          "model": "google/gemini-3.6-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-c694a36a5e4e3f09",
          "rated_matches": 44,
          "raw_elo_rating": 1432.0809863594432,
          "reasoning": "minimal",
          "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": 24.723237958811644,
          "uncertainty": 30.785599249992988,
          "unilateral_faults": 0,
          "wins": 1
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 116,
          "capped_draws": 92,
          "coverage_status": "rated",
          "distinct_rated_opponents": 56,
          "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": "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": 116,
          "raw_elo_rating": 1436.356567823582,
          "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": 27.91580429175553,
          "uncertainty": 2.4750163521024238,
          "unilateral_faults": 0,
          "wins": 3
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 106,
          "capped_draws": 79,
          "coverage_status": "rated",
          "distinct_rated_opponents": 50,
          "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": 106,
          "raw_elo_rating": 1415.6268161240855,
          "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": 25.257408425790306,
          "uncertainty": 4.586824452283178,
          "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": "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": "low",
          "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": 104,
          "capped_draws": 72,
          "coverage_status": "rated",
          "distinct_rated_opponents": 51,
          "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-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": 104,
          "raw_elo_rating": 1450.841570816661,
          "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": 29.38959639303247,
          "uncertainty": 5.045003647426665,
          "unilateral_faults": 0,
          "wins": 12
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 88,
          "capped_draws": 74,
          "coverage_status": "rated",
          "distinct_rated_opponents": 43,
          "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-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": 12,
          "model": "gpt-5.4-mini",
          "point_rating_method": "sequential_elo",
          "public_id": "E-bb8ac98c284a38ce",
          "rated_matches": 86,
          "raw_elo_rating": 1439.4052725343836,
          "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": 27.577174727119328,
          "uncertainty": 9.855626741889738,
          "unilateral_faults": 2,
          "wins": 0
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 106,
          "capped_draws": 89,
          "coverage_status": "rated",
          "distinct_rated_opponents": 52,
          "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-5.4-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": 106,
          "raw_elo_rating": 1411.3491671939846,
          "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": 24.750178678289455,
          "uncertainty": 4.586824452283178,
          "unilateral_faults": 0,
          "wins": 0
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 86,
          "capped_draws": 4,
          "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-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": 86,
          "raw_elo_rating": 1660.009150077097,
          "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": 53.73566761238275,
          "uncertainty": 9.855626741889738,
          "unilateral_faults": 0,
          "wins": 54
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 104,
          "capped_draws": 81,
          "coverage_status": "rated",
          "distinct_rated_opponents": 50,
          "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-5.5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_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": 104,
          "raw_elo_rating": 1439.4705060316537,
          "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": 28.041252381178502,
          "uncertainty": 5.045003647426665,
          "unilateral_faults": 0,
          "wins": 4
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 106,
          "capped_draws": 87,
          "coverage_status": "rated",
          "distinct_rated_opponents": 52,
          "draws": 87,
          "evaluated_setting_identity": {
            "canonical_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": 106,
          "raw_elo_rating": 1435.4850403755702,
          "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": 27.612132302735073,
          "uncertainty": 4.586824452283178,
          "unilateral_faults": 0,
          "wins": 1
        },
        {
          "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": 1539.1028287524625,
          "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": 39.5657581912891,
          "uncertainty": 8.09758473652126,
          "unilateral_faults": 0,
          "wins": 43
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 100,
          "capped_draws": 72,
          "coverage_status": "rated",
          "distinct_rated_opponents": 49,
          "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-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": 98,
          "raw_elo_rating": 1411.6697828592557,
          "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": 24.606530359301495,
          "uncertainty": 6.501890762960602,
          "unilateral_faults": 2,
          "wins": 3
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 156,
          "capped_draws": 136,
          "coverage_status": "rated",
          "distinct_rated_opponents": 59,
          "draws": 136,
          "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": 152,
          "raw_elo_rating": 1434.8991121674007,
          "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": 28.293408909065196,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 0
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 152,
          "capped_draws": 126,
          "coverage_status": "rated",
          "distinct_rated_opponents": 63,
          "draws": 126,
          "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": 152,
          "raw_elo_rating": 1408.9913624159817,
          "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": 25.221351903111337,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 5
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 110,
          "capped_draws": 99,
          "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": "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": 110,
          "raw_elo_rating": 1434.148802550992,
          "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": 27.537061582573646,
          "uncertainty": 3.707899787624953,
          "unilateral_faults": 0,
          "wins": 1
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 112,
          "capped_draws": 93,
          "coverage_status": "rated",
          "distinct_rated_opponents": 53,
          "draws": 93,
          "evaluated_setting_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": 112,
          "raw_elo_rating": 1439.5672369696829,
          "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": 28.219579865197666,
          "uncertainty": 3.286043419179858,
          "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": 1523.101241228136,
          "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": 37.77081834649088,
          "uncertainty": 7.017308256680951,
          "unilateral_faults": 0,
          "wins": 40
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 114,
          "capped_draws": 90,
          "coverage_status": "rated",
          "distinct_rated_opponents": 57,
          "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": "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": 114,
          "raw_elo_rating": 1403.1981627791558,
          "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": 23.94602226083568,
          "uncertainty": 2.875240412015687,
          "unilateral_faults": 0,
          "wins": 2
        },
        {
          "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": "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": 3,
          "model": "moonshotai/kimi-k3",
          "point_rating_method": "sequential_elo",
          "public_id": "E-3e1be56b9d966ded",
          "rated_matches": 52,
          "raw_elo_rating": 1817.7036945480477,
          "reasoning": "low",
          "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": 71.00457264118863,
          "uncertainty": 24.930281974344517,
          "unilateral_faults": 0,
          "wins": 49
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 108,
          "capped_draws": 94,
          "coverage_status": "rated",
          "distinct_rated_opponents": 53,
          "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": "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": 108,
          "raw_elo_rating": 1431.0354741384447,
          "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": 27.126778881865853,
          "uncertainty": 4.1413142610575715,
          "unilateral_faults": 0,
          "wins": 0
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 82,
          "capped_draws": 76,
          "coverage_status": "rated",
          "distinct_rated_opponents": 41,
          "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": "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": 82,
          "raw_elo_rating": 1448.6728163873909,
          "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": 28.55499914859909,
          "uncertainty": 11.132129994845172,
          "unilateral_faults": 0,
          "wins": 1
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 48,
          "capped_draws": 43,
          "coverage_status": "rated",
          "distinct_rated_opponents": 24,
          "draws": 43,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "low",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "o3",
            "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-21T14:20:15Z",
          "losses": 4,
          "model": "o3",
          "point_rating_method": "sequential_elo",
          "public_id": "E-335ae90fdc702bd6",
          "rated_matches": 48,
          "raw_elo_rating": 1459.8687978096345,
          "reasoning": "low",
          "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": 28.31296362033054,
          "uncertainty": 27.678571428571434,
          "unilateral_faults": 0,
          "wins": 1
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 52,
          "capped_draws": 32,
          "coverage_status": "rated",
          "distinct_rated_opponents": 26,
          "draws": 32,
          "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": 17,
          "model": "openai/gpt-oss-120b",
          "point_rating_method": "sequential_elo",
          "public_id": "E-f6e9da46c61ad315",
          "rated_matches": 52,
          "raw_elo_rating": 1389.000283498118,
          "reasoning": "low",
          "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": 20.170311463406588,
          "uncertainty": 24.930281974344517,
          "unilateral_faults": 0,
          "wins": 3
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 112,
          "capped_draws": 96,
          "coverage_status": "rated",
          "distinct_rated_opponents": 53,
          "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": "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": 112,
          "raw_elo_rating": 1421.9028148300824,
          "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": 26.124989933198123,
          "uncertainty": 3.286043419179858,
          "unilateral_faults": 0,
          "wins": 3
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 112,
          "capped_draws": 93,
          "coverage_status": "rated",
          "distinct_rated_opponents": 53,
          "draws": 93,
          "evaluated_setting_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": 112,
          "raw_elo_rating": 1424.7782920481748,
          "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": 26.465954703124442,
          "uncertainty": 3.286043419179858,
          "unilateral_faults": 0,
          "wins": 3
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 108,
          "capped_draws": 74,
          "coverage_status": "rated",
          "distinct_rated_opponents": 53,
          "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": "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": 108,
          "raw_elo_rating": 1416.188024322118,
          "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": 25.366216398962596,
          "uncertainty": 4.1413142610575715,
          "unilateral_faults": 0,
          "wins": 4
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 52,
          "capped_draws": 37,
          "coverage_status": "rated",
          "distinct_rated_opponents": 26,
          "draws": 37,
          "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": 15,
          "model": "stepfun/step-3.7-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-c38fe2712e69333b",
          "rated_matches": 52,
          "raw_elo_rating": 1382.0361210747858,
          "reasoning": "low",
          "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": 19.34452365209632,
          "uncertainty": 24.930281974344517,
          "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": "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": 112,
          "raw_elo_rating": 1436.4194727656443,
          "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": 27.84632818688169,
          "uncertainty": 3.286043419179858,
          "unilateral_faults": 0,
          "wins": 3
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 112,
          "capped_draws": 7,
          "coverage_status": "rated",
          "distinct_rated_opponents": 54,
          "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": 112,
          "raw_elo_rating": 1735.2256601683764,
          "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": 63.27779754414018,
          "uncertainty": 3.286043419179858,
          "unilateral_faults": 0,
          "wins": 68
        },
        {
          "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": "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": 8,
          "model": "x-ai/grok-4.5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-b914d026c7631fcb",
          "rated_matches": 52,
          "raw_elo_rating": 1773.667375508612,
          "reasoning": "low",
          "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": 65.78288863854351,
          "uncertainty": 24.930281974344517,
          "unilateral_faults": 0,
          "wins": 44
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 94,
          "capped_draws": 58,
          "coverage_status": "rated",
          "distinct_rated_opponents": 47,
          "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": "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": 94,
          "raw_elo_rating": 1347.149327600217,
          "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": 16.856581427150502,
          "uncertainty": 7.54891760425771,
          "unilateral_faults": 0,
          "wins": 2
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 90,
          "capped_draws": 72,
          "coverage_status": "rated",
          "distinct_rated_opponents": 45,
          "draws": 72,
          "evaluated_setting_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": 90,
          "raw_elo_rating": 1426.5039592688865,
          "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": 26.160395258498756,
          "uncertainty": 8.664241836095918,
          "unilateral_faults": 0,
          "wins": 2
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 78,
          "capped_draws": 62,
          "coverage_status": "rated",
          "distinct_rated_opponents": 39,
          "draws": 62,
          "evaluated_setting_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": 78,
          "raw_elo_rating": 1430.648090819964,
          "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": 26.287510609619638,
          "uncertainty": 12.5043950463012,
          "unilateral_faults": 0,
          "wins": 3
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 68,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 34,
          "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": 68,
          "raw_elo_rating": 1753.6029652961001,
          "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": 64.20883838011629,
          "uncertainty": 16.4429265428846,
          "unilateral_faults": 0,
          "wins": 50
        }
      ]
    },
    "full_freedom/intensive": {
      "GB2-01": [
        {
          "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": "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": 98,
          "raw_elo_rating": 1810.7971143350485,
          "reasoning": "xhigh",
          "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": 79.68193767817715,
          "uncertainty": 6.501890762960602,
          "unilateral_faults": 0,
          "wins": 63
        },
        {
          "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": "legacy_shared_thinking_budget",
          "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": 42,
          "capped_draws": 3,
          "coverage_status": "rated",
          "distinct_rated_opponents": 21,
          "draws": 3,
          "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": 11,
          "model": "claude-opus-4-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-5b675f86b98132f4",
          "rated_matches": 42,
          "raw_elo_rating": 1622.7522359918837,
          "reasoning": "high",
          "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": 57.24531251291242,
          "uncertainty": 32.49928516630233,
          "unilateral_faults": 0,
          "wins": 28
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 102,
          "capped_draws": 14,
          "coverage_status": "rated",
          "distinct_rated_opponents": 48,
          "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-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": 102,
          "raw_elo_rating": 1604.793115128391,
          "reasoning": "xhigh",
          "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": 57.63498693048245,
          "uncertainty": 5.516463908214657,
          "unilateral_faults": 0,
          "wins": 52
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 68,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 30,
          "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": 68,
          "raw_elo_rating": 1844.4582749578583,
          "reasoning": "xhigh",
          "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": 82.44386303842391,
          "uncertainty": 16.4429265428846,
          "unilateral_faults": 0,
          "wins": 50
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 56,
          "capped_draws": 1,
          "coverage_status": "rated",
          "distinct_rated_opponents": 27,
          "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-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": 28,
          "model": "claude-opus-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-bf06fe9df8858291",
          "rated_matches": 56,
          "raw_elo_rating": 1489.1036178344127,
          "reasoning": "xhigh",
          "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": 43.74844229033586,
          "uncertainty": 22.47661785325219,
          "unilateral_faults": 0,
          "wins": 27
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 92,
          "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": 49,
          "model": "deepseek/deepseek-v4-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-b9882650a0cde9ac",
          "rated_matches": 92,
          "raw_elo_rating": 1382.025506422629,
          "reasoning": "xhigh",
          "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": 33.4805377654376,
          "uncertainty": 8.09758473652126,
          "unilateral_faults": 0,
          "wins": 25
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 96,
          "capped_draws": 19,
          "coverage_status": "rated",
          "distinct_rated_opponents": 47,
          "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": 44,
          "model": "deepseek/deepseek-v4-pro",
          "point_rating_method": "sequential_elo",
          "public_id": "E-e192048d4eaa3c43",
          "rated_matches": 96,
          "raw_elo_rating": 1475.4991443772221,
          "reasoning": "xhigh",
          "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": 43.61554479729633,
          "uncertainty": 7.017308256680951,
          "unilateral_faults": 0,
          "wins": 33
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 26,
          "capped_draws": 3,
          "coverage_status": "under_covered",
          "distinct_rated_opponents": 13,
          "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": "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-85d9dd9fbf531322",
          "rated_matches": 26,
          "raw_elo_rating": 1387.6764784941386,
          "reasoning": "high",
          "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": 30.273553237196605,
          "uncertainty": 52.475044864937615,
          "unilateral_faults": 0,
          "wins": 8
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 46,
          "capped_draws": 5,
          "coverage_status": "rated",
          "distinct_rated_opponents": 23,
          "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-3.6-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": 15,
          "model": "google/gemini-3.6-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-df0493ecef384a6a",
          "rated_matches": 46,
          "raw_elo_rating": 1596.815395617423,
          "reasoning": "high",
          "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": 54.743904123110745,
          "uncertainty": 29.182495748947275,
          "unilateral_faults": 0,
          "wins": 26
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 46,
          "capped_draws": 12,
          "coverage_status": "rated",
          "distinct_rated_opponents": 23,
          "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": 21,
          "model": "google/gemini-3.6-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-e9260a0da3a64563",
          "rated_matches": 46,
          "raw_elo_rating": 1457.3459738996155,
          "reasoning": "high",
          "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": 39.760274191838555,
          "uncertainty": 29.182495748947275,
          "unilateral_faults": 0,
          "wins": 13
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 50,
          "capped_draws": 2,
          "coverage_status": "rated",
          "distinct_rated_opponents": 25,
          "draws": 2,
          "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-3e63b136f656e976",
          "rated_matches": 50,
          "raw_elo_rating": 1409.0098425181743,
          "reasoning": "high",
          "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": 34.818208622235126,
          "uncertainty": 26.264004201400486,
          "unilateral_faults": 0,
          "wins": 16
        },
        {
          "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": "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": 94,
          "raw_elo_rating": 2000.7576930253301,
          "reasoning": "xhigh",
          "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": 7.54891760425771,
          "unilateral_faults": 0,
          "wins": 89
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 96,
          "capped_draws": 29,
          "coverage_status": "rated",
          "distinct_rated_opponents": 44,
          "draws": 29,
          "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": 96,
          "raw_elo_rating": 1751.3774293727092,
          "reasoning": "xhigh",
          "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": 73.2539994315327,
          "uncertainty": 7.017308256680951,
          "unilateral_faults": 0,
          "wins": 51
        },
        {
          "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": "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": 94,
          "raw_elo_rating": 1821.051700392042,
          "reasoning": "xhigh",
          "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": 80.69363121403609,
          "uncertainty": 7.54891760425771,
          "unilateral_faults": 0,
          "wins": 62
        },
        {
          "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": "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": 100,
          "raw_elo_rating": 1842.1038472104176,
          "reasoning": "xhigh",
          "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": 83.08829242248612,
          "uncertainty": 6.001859510499461,
          "unilateral_faults": 0,
          "wins": 77
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 100,
          "capped_draws": 31,
          "coverage_status": "rated",
          "distinct_rated_opponents": 46,
          "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": 40,
          "model": "gpt-5.6-terra",
          "point_rating_method": "sequential_elo",
          "public_id": "E-36d36f4895d90b11",
          "rated_matches": 100,
          "raw_elo_rating": 1467.9188616540573,
          "reasoning": "xhigh",
          "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": 42.88844588724325,
          "uncertainty": 6.001859510499461,
          "unilateral_faults": 0,
          "wins": 29
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 44,
          "capped_draws": 2,
          "coverage_status": "rated",
          "distinct_rated_opponents": 22,
          "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": "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": 41,
          "model": "mistralai/mistral-medium-3-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-99c7b0d758665b66",
          "rated_matches": 44,
          "raw_elo_rating": 1185.7659955378595,
          "reasoning": "high",
          "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": 10.445818809147307,
          "uncertainty": 30.785599249992988,
          "unilateral_faults": 0,
          "wins": 1
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 44,
          "capped_draws": 2,
          "coverage_status": "rated",
          "distinct_rated_opponents": 22,
          "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": "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": 22,
          "model": "moonshotai/kimi-k3",
          "point_rating_method": "sequential_elo",
          "public_id": "E-dbb89dcf5242a5a0",
          "rated_matches": 44,
          "raw_elo_rating": 1513.6885084246553,
          "reasoning": "max",
          "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": 45.67554528761618,
          "uncertainty": 30.785599249992988,
          "unilateral_faults": 0,
          "wins": 20
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 44,
          "capped_draws": 3,
          "coverage_status": "rated",
          "distinct_rated_opponents": 22,
          "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": "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": 37,
          "model": "nvidia/nemotron-3-ultra-550b-a55b",
          "point_rating_method": "sequential_elo",
          "public_id": "E-ce064a9927030b28",
          "rated_matches": 44,
          "raw_elo_rating": 1255.6725026396348,
          "reasoning": "high",
          "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": 17.9560903747683,
          "uncertainty": 30.785599249992988,
          "unilateral_faults": 0,
          "wins": 4
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 48,
          "capped_draws": 1,
          "coverage_status": "rated",
          "distinct_rated_opponents": 24,
          "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-03T15:45:00Z",
          "losses": 20,
          "model": "o3",
          "point_rating_method": "sequential_elo",
          "public_id": "E-01ad69b67b42a9e7",
          "rated_matches": 48,
          "raw_elo_rating": 1570.1252117794763,
          "reasoning": "high",
          "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": 52.005752373767585,
          "uncertainty": 27.678571428571434,
          "unilateral_faults": 0,
          "wins": 27
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 48,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 24,
          "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-03T16:00:00Z",
          "losses": 18,
          "model": "o3",
          "point_rating_method": "sequential_elo",
          "public_id": "E-21b0558e9f2190f7",
          "rated_matches": 48,
          "raw_elo_rating": 1622.4157835264396,
          "reasoning": "high",
          "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": 57.623489697841514,
          "uncertainty": 27.678571428571434,
          "unilateral_faults": 0,
          "wins": 30
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 26,
          "capped_draws": 5,
          "coverage_status": "under_covered",
          "distinct_rated_opponents": 13,
          "draws": 5,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "o3",
            "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-03T15:50:00Z",
          "losses": 14,
          "model": "o3",
          "point_rating_method": "sequential_elo",
          "public_id": "E-5e8b87fcfa2225fd",
          "rated_matches": 26,
          "raw_elo_rating": 1451.401909856562,
          "reasoning": "high",
          "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": 37.11977278112783,
          "uncertainty": 52.475044864937615,
          "unilateral_faults": 0,
          "wins": 7
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 42,
          "capped_draws": 1,
          "coverage_status": "rated",
          "distinct_rated_opponents": 21,
          "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": "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": 39,
          "model": "stepfun/step-3.7-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-4b0ce2bc67b08d8a",
          "rated_matches": 42,
          "raw_elo_rating": 1196.3552850945189,
          "reasoning": "high",
          "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": 11.436173582115469,
          "uncertainty": 32.49928516630233,
          "unilateral_faults": 0,
          "wins": 2
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 46,
          "capped_draws": 4,
          "coverage_status": "rated",
          "distinct_rated_opponents": 23,
          "draws": 4,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "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": 16,
          "model": "tencent/hy3-preview",
          "point_rating_method": "sequential_elo",
          "public_id": "E-29e8870e43d717e5",
          "rated_matches": 46,
          "raw_elo_rating": 1572.2892822260337,
          "reasoning": "high",
          "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": 52.1089881524075,
          "uncertainty": 29.182495748947275,
          "unilateral_faults": 0,
          "wins": 26
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 28,
          "capped_draws": 15,
          "coverage_status": "under_covered",
          "distinct_rated_opponents": 14,
          "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",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "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-ab1de1dc51400446",
          "rated_matches": 28,
          "raw_elo_rating": 1354.9663293370681,
          "reasoning": "max",
          "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": 27.049674587596016,
          "uncertainty": 49.09766908852594,
          "unilateral_faults": 0,
          "wins": 2
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 36,
          "capped_draws": 6,
          "coverage_status": "under_covered",
          "distinct_rated_opponents": 18,
          "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": "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": 6,
          "model": "x-ai/grok-4.5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-1c8e452ede41ea2e",
          "rated_matches": 36,
          "raw_elo_rating": 1677.8705995787811,
          "reasoning": "high",
          "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": 62.6554488390747,
          "uncertainty": 38.449493652678655,
          "unilateral_faults": 0,
          "wins": 24
        },
        {
          "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": 1251.9402308692768,
          "reasoning": "high",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "repaired",
          "score": 18.9315557741441,
          "uncertainty": 14.770573598065289,
          "unilateral_faults": 0,
          "wins": 2
        }
      ],
      "GB2-02": [
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 82,
          "capped_draws": 0,
          "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-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": 82,
          "raw_elo_rating": 1701.6468619133602,
          "reasoning": "xhigh",
          "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": 75.80812316419362,
          "uncertainty": 11.132129994845172,
          "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": "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": "legacy_shared_thinking_budget",
          "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": 30,
          "capped_draws": 0,
          "coverage_status": "under_covered",
          "distinct_rated_opponents": 15,
          "draws": 23,
          "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": 7,
          "model": "claude-opus-4-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-63fde27ceab11930",
          "rated_matches": 30,
          "raw_elo_rating": 1434.0593552461078,
          "reasoning": "high",
          "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": 8.52361085885523,
          "uncertainty": 46.05265101338746,
          "unilateral_faults": 0,
          "wins": 0
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 82,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 35,
          "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": 82,
          "raw_elo_rating": 1729.077401945733,
          "reasoning": "xhigh",
          "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": 82.05347374902418,
          "uncertainty": 11.132129994845172,
          "unilateral_faults": 0,
          "wins": 45
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 56,
          "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": 56,
          "raw_elo_rating": 1636.8705409386753,
          "reasoning": "xhigh",
          "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": 58.99361361961407,
          "uncertainty": 22.47661785325219,
          "unilateral_faults": 0,
          "wins": 21
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 58,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 23,
          "draws": 12,
          "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": 58,
          "raw_elo_rating": 1750.208365973637,
          "reasoning": "xhigh",
          "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": 85.00444139491074,
          "uncertainty": 21.344455490411935,
          "unilateral_faults": 0,
          "wins": 35
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 70,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 35,
          "draws": 57,
          "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": 9,
          "model": "deepseek/deepseek-v4-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-12dcb25370550495",
          "rated_matches": 70,
          "raw_elo_rating": 1496.9276220539098,
          "reasoning": "xhigh",
          "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": 28.386103413880857,
          "uncertainty": 15.58908290969266,
          "unilateral_faults": 0,
          "wins": 4
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 20,
          "capped_draws": 0,
          "coverage_status": "under_covered",
          "distinct_rated_opponents": 10,
          "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": "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": 3,
          "model": "google/gemini-3.5-flash-lite",
          "point_rating_method": "sequential_elo",
          "public_id": "E-423f6c31467b8943",
          "rated_matches": 20,
          "raw_elo_rating": 1469.3649644456032,
          "reasoning": "high",
          "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": 13.045441153620832,
          "uncertainty": 65.3589451179962,
          "unilateral_faults": 0,
          "wins": 1
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 32,
          "capped_draws": 0,
          "coverage_status": "under_covered",
          "distinct_rated_opponents": 16,
          "draws": 22,
          "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": 8,
          "model": "gpt-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-5bccb9b671ce5eae",
          "rated_matches": 32,
          "raw_elo_rating": 1451.374404650968,
          "reasoning": "high",
          "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": 12.969290339907706,
          "uncertainty": 43.288827977848925,
          "unilateral_faults": 0,
          "wins": 2
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 80,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 35,
          "draws": 49,
          "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": 80,
          "raw_elo_rating": 1620.5373124406053,
          "reasoning": "xhigh",
          "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": 57.21854400867016,
          "uncertainty": 11.805555555555554,
          "unilateral_faults": 0,
          "wins": 22
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 84,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 42,
          "draws": 71,
          "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": 84,
          "raw_elo_rating": 1469.0532689115892,
          "reasoning": "xhigh",
          "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": 22.96981343482104,
          "uncertainty": 10.482614454664043,
          "unilateral_faults": 0,
          "wins": 3
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 86,
          "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": 86,
          "raw_elo_rating": 1806.880102034298,
          "reasoning": "xhigh",
          "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": 9.855626741889738,
          "unilateral_faults": 0,
          "wins": 60
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 86,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 37,
          "draws": 50,
          "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": 86,
          "raw_elo_rating": 1580.2699961396245,
          "reasoning": "xhigh",
          "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": 48.40569833085461,
          "uncertainty": 9.855626741889738,
          "unilateral_faults": 0,
          "wins": 16
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 32,
          "capped_draws": 0,
          "coverage_status": "under_covered",
          "distinct_rated_opponents": 16,
          "draws": 22,
          "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": 8,
          "model": "moonshotai/kimi-k3",
          "point_rating_method": "sequential_elo",
          "public_id": "E-1beeecccf3f2c84f",
          "rated_matches": 32,
          "raw_elo_rating": 1475.6155697362992,
          "reasoning": "max",
          "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": 18.48848807950653,
          "uncertainty": 43.288827977848925,
          "unilateral_faults": 0,
          "wins": 2
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 32,
          "capped_draws": 0,
          "coverage_status": "under_covered",
          "distinct_rated_opponents": 16,
          "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": "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": 6,
          "model": "nvidia/nemotron-3-ultra-550b-a55b",
          "point_rating_method": "sequential_elo",
          "public_id": "E-2404d10bab26a254",
          "rated_matches": 32,
          "raw_elo_rating": 1461.4453871714331,
          "reasoning": "high",
          "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": 15.262238874634908,
          "uncertainty": 43.288827977848925,
          "unilateral_faults": 0,
          "wins": 0
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 34,
          "capped_draws": 0,
          "coverage_status": "under_covered",
          "distinct_rated_opponents": 17,
          "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": "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": 10,
          "model": "nvidia/nemotron-3-ultra-550b-a55b",
          "point_rating_method": "sequential_elo",
          "public_id": "E-abd2cae3e3ff9bdb",
          "rated_matches": 34,
          "raw_elo_rating": 1442.551306509627,
          "reasoning": "high",
          "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": 11.42007860588387,
          "uncertainty": 40.76542547285167,
          "unilateral_faults": 0,
          "wins": 1
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 32,
          "capped_draws": 0,
          "coverage_status": "under_covered",
          "distinct_rated_opponents": 16,
          "draws": 21,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "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-e5b4a3586049e1c9",
          "rated_matches": 32,
          "raw_elo_rating": 1412.4140830180731,
          "reasoning": "high",
          "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": 4.098853694911825,
          "uncertainty": 43.288827977848925,
          "unilateral_faults": 0,
          "wins": 0
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 30,
          "capped_draws": 0,
          "coverage_status": "under_covered",
          "distinct_rated_opponents": 14,
          "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": "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": 11,
          "model": "tencent/hy3-preview",
          "point_rating_method": "sequential_elo",
          "public_id": "E-fbf6af15f65f01d7",
          "rated_matches": 28,
          "raw_elo_rating": 1399.058360252803,
          "reasoning": "high",
          "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": 0.0,
          "uncertainty": 49.09766908852594,
          "unilateral_faults": 2,
          "wins": 0
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 16,
          "capped_draws": 0,
          "coverage_status": "under_covered",
          "distinct_rated_opponents": 7,
          "draws": 13,
          "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": 0,
          "model": "thinkingmachines/inkling",
          "point_rating_method": "sequential_elo",
          "public_id": "E-9468e854340a4e9b",
          "rated_matches": 14,
          "raw_elo_rating": 1491.1086378377042,
          "reasoning": "max",
          "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": 14.354883833993085,
          "uncertainty": 85.34944487358055,
          "unilateral_faults": 0,
          "wins": 1
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 32,
          "capped_draws": 0,
          "coverage_status": "under_covered",
          "distinct_rated_opponents": 16,
          "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": "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": 8,
          "model": "x-ai/grok-4.5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-0576181f89efa7a7",
          "rated_matches": 32,
          "raw_elo_rating": 1522.169443824012,
          "reasoning": "high",
          "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": 29.0878151221639,
          "uncertainty": 43.288827977848925,
          "unilateral_faults": 0,
          "wins": 8
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 70,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 35,
          "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": "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": 70,
          "raw_elo_rating": 1505.0662350094012,
          "reasoning": "high",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "repaired",
          "score": 30.2390924954411,
          "uncertainty": 15.58908290969266,
          "unilateral_faults": 0,
          "wins": 3
        }
      ],
      "GB2-03": [
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 64,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 29,
          "draws": 30,
          "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": 64,
          "raw_elo_rating": 1700.3473191690596,
          "reasoning": "xhigh",
          "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": 70.49045424400458,
          "uncertainty": 18.26736729460423,
          "unilateral_faults": 0,
          "wins": 27
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 24,
          "capped_draws": 1,
          "coverage_status": "under_covered",
          "distinct_rated_opponents": 12,
          "draws": 6,
          "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": 14,
          "model": "claude-opus-4-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-d5810442d7094396",
          "rated_matches": 24,
          "raw_elo_rating": 1384.726716888602,
          "reasoning": "high",
          "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": 17.7111628193571,
          "uncertainty": 56.25,
          "unilateral_faults": 0,
          "wins": 4
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 56,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 24,
          "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": 56,
          "raw_elo_rating": 1897.1712916753029,
          "reasoning": "xhigh",
          "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": 22.47661785325219,
          "unilateral_faults": 0,
          "wins": 52
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 56,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 24,
          "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": 56,
          "raw_elo_rating": 1875.9966416414663,
          "reasoning": "xhigh",
          "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": 96.77005388139995,
          "uncertainty": 22.47661785325219,
          "unilateral_faults": 0,
          "wins": 51
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 76,
          "capped_draws": 1,
          "coverage_status": "rated",
          "distinct_rated_opponents": 35,
          "draws": 36,
          "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": 76,
          "raw_elo_rating": 1595.279480462201,
          "reasoning": "xhigh",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_7fad32_to_brackets_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "xhigh",
          "repair_status": "first_pass",
          "score": 55.078257956466814,
          "uncertainty": 13.230288229818967,
          "unilateral_faults": 0,
          "wins": 24
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 98,
          "capped_draws": 3,
          "coverage_status": "rated",
          "distinct_rated_opponents": 45,
          "draws": 34,
          "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": 32,
          "model": "claude-sonnet-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-d49e8df479ed0377",
          "rated_matches": 98,
          "raw_elo_rating": 1552.5070357171141,
          "reasoning": "xhigh",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_7fad32_to_brackets_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "xhigh",
          "repair_status": "first_pass",
          "score": 49.374890832643544,
          "uncertainty": 6.501890762960602,
          "unilateral_faults": 0,
          "wins": 32
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 38,
          "capped_draws": 1,
          "coverage_status": "under_covered",
          "distinct_rated_opponents": 19,
          "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",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_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": "google/gemini-3.5-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-46c3bb79de67d970",
          "rated_matches": 38,
          "raw_elo_rating": 1480.0032664035127,
          "reasoning": "high",
          "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": 34.67728441611023,
          "uncertainty": 36.31407690254356,
          "unilateral_faults": 0,
          "wins": 6
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 24,
          "capped_draws": 0,
          "coverage_status": "under_covered",
          "distinct_rated_opponents": 12,
          "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": "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": 11,
          "model": "google/gemini-3.5-flash-lite",
          "point_rating_method": "sequential_elo",
          "public_id": "E-7ed90f1b43d80cf9",
          "rated_matches": 24,
          "raw_elo_rating": 1505.3722146616713,
          "reasoning": "high",
          "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": 36.1142276462138,
          "uncertainty": 56.25,
          "unilateral_faults": 0,
          "wins": 10
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 24,
          "capped_draws": 1,
          "coverage_status": "under_covered",
          "distinct_rated_opponents": 12,
          "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": "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": 11,
          "model": "google/gemini-3.5-flash-lite",
          "point_rating_method": "sequential_elo",
          "public_id": "E-d485651284072880",
          "rated_matches": 24,
          "raw_elo_rating": 1464.0261492484403,
          "reasoning": "high",
          "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": 29.807367165051325,
          "uncertainty": 56.25,
          "unilateral_faults": 0,
          "wins": 6
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 26,
          "capped_draws": 0,
          "coverage_status": "under_covered",
          "distinct_rated_opponents": 13,
          "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": "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-97580ecf1bd06d40",
          "rated_matches": 26,
          "raw_elo_rating": 1602.1008415430224,
          "reasoning": "high",
          "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": 51.32971285079575,
          "uncertainty": 52.475044864937615,
          "unilateral_faults": 0,
          "wins": 15
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 29,
          "capped_draws": 1,
          "coverage_status": "under_covered",
          "distinct_rated_opponents": 14,
          "draws": 8,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 14,
          "model": "gpt-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-cc568b7069d5a0fd",
          "rated_matches": 28,
          "raw_elo_rating": 1399.4380048256987,
          "reasoning": "high",
          "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": 20.82800215505983,
          "uncertainty": 49.09766908852594,
          "unilateral_faults": 1,
          "wins": 6
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 60,
          "capped_draws": 7,
          "coverage_status": "rated",
          "distinct_rated_opponents": 29,
          "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": 24,
          "model": "gpt-5.4",
          "point_rating_method": "sequential_elo",
          "public_id": "E-4b75acaf58f14113",
          "rated_matches": 58,
          "raw_elo_rating": 1449.7947632570085,
          "reasoning": "xhigh",
          "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": 31.89608232157542,
          "uncertainty": 21.344455490411935,
          "unilateral_faults": 2,
          "wins": 17
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 81,
          "capped_draws": 3,
          "coverage_status": "rated",
          "distinct_rated_opponents": 40,
          "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": 80,
          "raw_elo_rating": 1530.3839322567405,
          "reasoning": "xhigh",
          "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": 45.35305938673562,
          "uncertainty": 11.805555555555554,
          "unilateral_faults": 0,
          "wins": 21
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 64,
          "capped_draws": 2,
          "coverage_status": "rated",
          "distinct_rated_opponents": 31,
          "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": 64,
          "raw_elo_rating": 1341.726476188212,
          "reasoning": "xhigh",
          "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": 15.787023585925473,
          "uncertainty": 18.26736729460423,
          "unilateral_faults": 0,
          "wins": 6
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 68,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 29,
          "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": 68,
          "raw_elo_rating": 1616.3799977137346,
          "reasoning": "xhigh",
          "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": 57.90485555225239,
          "uncertainty": 16.4429265428846,
          "unilateral_faults": 0,
          "wins": 35
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 58,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 27,
          "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": 58,
          "raw_elo_rating": 1584.7107585816805,
          "reasoning": "xhigh",
          "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": 52.47594525860797,
          "uncertainty": 21.344455490411935,
          "unilateral_faults": 0,
          "wins": 27
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 26,
          "capped_draws": 0,
          "coverage_status": "under_covered",
          "distinct_rated_opponents": 13,
          "draws": 11,
          "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": 9,
          "model": "moonshotai/kimi-k3",
          "point_rating_method": "sequential_elo",
          "public_id": "E-8f139a9e4d538859",
          "rated_matches": 26,
          "raw_elo_rating": 1498.1810215922073,
          "reasoning": "max",
          "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": 35.477955274666584,
          "uncertainty": 52.475044864937615,
          "unilateral_faults": 0,
          "wins": 6
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 26,
          "capped_draws": 1,
          "coverage_status": "under_covered",
          "distinct_rated_opponents": 12,
          "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": "o3",
            "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-03T16:00:00Z",
          "losses": 8,
          "model": "o3",
          "point_rating_method": "sequential_elo",
          "public_id": "E-9f7b8b1adc2ddba7",
          "rated_matches": 24,
          "raw_elo_rating": 1459.4837652461133,
          "reasoning": "high",
          "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": 29.11447941701005,
          "uncertainty": 56.25,
          "unilateral_faults": 0,
          "wins": 7
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 26,
          "capped_draws": 0,
          "coverage_status": "under_covered",
          "distinct_rated_opponents": 13,
          "draws": 11,
          "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-f9259c1ced4fba75",
          "rated_matches": 26,
          "raw_elo_rating": 1476.4317562753513,
          "reasoning": "max",
          "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": 32.16035829052158,
          "uncertainty": 52.475044864937615,
          "unilateral_faults": 0,
          "wins": 6
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 34,
          "capped_draws": 3,
          "coverage_status": "under_covered",
          "distinct_rated_opponents": 17,
          "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": "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": 11,
          "model": "x-ai/grok-4.5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-c0c60ca46f3ce498",
          "rated_matches": 34,
          "raw_elo_rating": 1432.2090815157947,
          "reasoning": "high",
          "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": 26.84363736482782,
          "uncertainty": 40.76542547285167,
          "unilateral_faults": 0,
          "wins": 5
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 34,
          "capped_draws": 3,
          "coverage_status": "under_covered",
          "distinct_rated_opponents": 17,
          "draws": 8,
          "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": 12,
          "model": "z-ai/glm-5.2",
          "point_rating_method": "sequential_elo",
          "public_id": "E-d047860be3ae0d90",
          "rated_matches": 34,
          "raw_elo_rating": 1508.7509672095766,
          "reasoning": "xhigh",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_7fad32_to_brackets_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "xhigh",
          "repair_status": "first_pass",
          "score": 38.519210099767925,
          "uncertainty": 40.76542547285167,
          "unilateral_faults": 0,
          "wins": 14
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 32,
          "capped_draws": 1,
          "coverage_status": "under_covered",
          "distinct_rated_opponents": 16,
          "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": "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": 6,
          "model": "z-ai/glm-5.2",
          "point_rating_method": "sequential_elo",
          "public_id": "E-d3a5bd501d8146e0",
          "rated_matches": 32,
          "raw_elo_rating": 1558.4052871388826,
          "reasoning": "xhigh",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_7fad32_to_brackets_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "xhigh",
          "repair_status": "first_pass",
          "score": 45.78546547495367,
          "uncertainty": 43.288827977848925,
          "unilateral_faults": 0,
          "wins": 13
        }
      ],
      "GB2-04": [
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 98,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 44,
          "draws": 17,
          "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": 98,
          "raw_elo_rating": 1865.823673582791,
          "reasoning": "xhigh",
          "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": 6.501890762960602,
          "unilateral_faults": 0,
          "wins": 76
        },
        {
          "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": "legacy_shared_thinking_budget",
          "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": 40,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 20,
          "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": 22,
          "model": "claude-opus-4-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-f40463f635c43598",
          "rated_matches": 40,
          "raw_elo_rating": 1337.681790240821,
          "reasoning": "high",
          "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": 0.0,
          "uncertainty": 34.33688094430304,
          "unilateral_faults": 0,
          "wins": 1
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 92,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 41,
          "draws": 35,
          "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": 92,
          "raw_elo_rating": 1623.201730875163,
          "reasoning": "xhigh",
          "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": 55.68784123456057,
          "uncertainty": 8.09758473652126,
          "unilateral_faults": 0,
          "wins": 40
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 78,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 35,
          "draws": 10,
          "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": 78,
          "raw_elo_rating": 1694.3212314288232,
          "reasoning": "xhigh",
          "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": 67.96851702113216,
          "uncertainty": 12.5043950463012,
          "unilateral_faults": 0,
          "wins": 55
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 82,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 36,
          "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": 82,
          "raw_elo_rating": 1819.8717146747888,
          "reasoning": "xhigh",
          "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": 90.97833223839412,
          "uncertainty": 11.132129994845172,
          "unilateral_faults": 0,
          "wins": 61
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 86,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 43,
          "draws": 52,
          "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": 86,
          "raw_elo_rating": 1465.1059463245633,
          "reasoning": "xhigh",
          "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": 26.709033756995762,
          "uncertainty": 9.855626741889738,
          "unilateral_faults": 0,
          "wins": 9
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 46,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 23,
          "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-3.1-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": 15,
          "model": "google/gemini-3.1-flash-lite",
          "point_rating_method": "sequential_elo",
          "public_id": "E-2be6f5c895691cb3",
          "rated_matches": 46,
          "raw_elo_rating": 1404.0919377589096,
          "reasoning": "high",
          "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": 12.814751118329694,
          "uncertainty": 29.182495748947275,
          "unilateral_faults": 0,
          "wins": 3
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 46,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 23,
          "draws": 10,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "google/gemini-3.5-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": 25,
          "model": "google/gemini-3.5-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-8e95359e4cbd1851",
          "rated_matches": 46,
          "raw_elo_rating": 1415.7715836747748,
          "reasoning": "high",
          "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": 14.936741735872697,
          "uncertainty": 29.182495748947275,
          "unilateral_faults": 0,
          "wins": 11
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 40,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 20,
          "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": "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-39ebef34ae0ea1cb",
          "rated_matches": 40,
          "raw_elo_rating": 1409.207990249776,
          "reasoning": "high",
          "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": 12.995079338949578,
          "uncertainty": 34.33688094430304,
          "unilateral_faults": 0,
          "wins": 4
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 42,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 21,
          "draws": 21,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "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": 11,
          "model": "google/gemini-3.5-flash-lite",
          "point_rating_method": "sequential_elo",
          "public_id": "E-953992515ec1424d",
          "rated_matches": 42,
          "raw_elo_rating": 1510.908533785498,
          "reasoning": "high",
          "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": 31.739405113778663,
          "uncertainty": 32.49928516630233,
          "unilateral_faults": 0,
          "wins": 10
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 38,
          "capped_draws": 0,
          "coverage_status": "under_covered",
          "distinct_rated_opponents": 19,
          "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
            "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": "google/gemini-3.6-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-a5a73c81dfcf4540",
          "rated_matches": 38,
          "raw_elo_rating": 1384.2675212009046,
          "reasoning": "high",
          "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": 8.176447443583427,
          "uncertainty": 36.31407690254356,
          "unilateral_faults": 0,
          "wins": 6
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 40,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 20,
          "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": "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-ccfb6c993d1622b0",
          "rated_matches": 40,
          "raw_elo_rating": 1579.4624729655434,
          "reasoning": "high",
          "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": 43.92738820515834,
          "uncertainty": 34.33688094430304,
          "unilateral_faults": 0,
          "wins": 19
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 46,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 23,
          "draws": 27,
          "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": 15,
          "model": "gpt-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-7e3da77777a95e31",
          "rated_matches": 46,
          "raw_elo_rating": 1423.0741008790983,
          "reasoning": "high",
          "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": 16.26348341140345,
          "uncertainty": 29.182495748947275,
          "unilateral_faults": 0,
          "wins": 4
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 94,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 42,
          "draws": 34,
          "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": 94,
          "raw_elo_rating": 1635.5726584504935,
          "reasoning": "xhigh",
          "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": 58.01517252922639,
          "uncertainty": 7.54891760425771,
          "unilateral_faults": 0,
          "wins": 36
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 84,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 41,
          "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": 33,
          "model": "gpt-5.5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-64bf5daf186f8119",
          "rated_matches": 84,
          "raw_elo_rating": 1401.941773211182,
          "reasoning": "xhigh",
          "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": 15.142060466906322,
          "uncertainty": 10.482614454664043,
          "unilateral_faults": 0,
          "wins": 6
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 82,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 40,
          "draws": 42,
          "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": 24,
          "model": "gpt-5.6-luna",
          "point_rating_method": "sequential_elo",
          "public_id": "E-e348813cda8b38b7",
          "rated_matches": 82,
          "raw_elo_rating": 1492.3136234631593,
          "reasoning": "xhigh",
          "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": 31.466665424316382,
          "uncertainty": 11.132129994845172,
          "unilateral_faults": 0,
          "wins": 16
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 94,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 43,
          "draws": 42,
          "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": 94,
          "raw_elo_rating": 1656.1290756470048,
          "reasoning": "xhigh",
          "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": 61.74991968984401,
          "uncertainty": 7.54891760425771,
          "unilateral_faults": 0,
          "wins": 46
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 90,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 43,
          "draws": 41,
          "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": 90,
          "raw_elo_rating": 1561.9585279553617,
          "reasoning": "xhigh",
          "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": 44.4786439895316,
          "uncertainty": 8.664241836095918,
          "unilateral_faults": 0,
          "wins": 31
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 44,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 22,
          "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": "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": 9,
          "model": "moonshotai/kimi-k3",
          "point_rating_method": "sequential_elo",
          "public_id": "E-601725df2c678708",
          "rated_matches": 44,
          "raw_elo_rating": 1573.7970134206257,
          "reasoning": "max",
          "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": 43.41423713079391,
          "uncertainty": 30.785599249992988,
          "unilateral_faults": 0,
          "wins": 19
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 46,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 23,
          "draws": 27,
          "evaluated_setting_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": 15,
          "model": "nvidia/nemotron-3-ultra-550b-a55b",
          "point_rating_method": "sequential_elo",
          "public_id": "E-958dea26b779a042",
          "rated_matches": 46,
          "raw_elo_rating": 1416.7179169940546,
          "reasoning": "high",
          "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": 15.108674210456737,
          "uncertainty": 29.182495748947275,
          "unilateral_faults": 0,
          "wins": 4
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 46,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 23,
          "draws": 22,
          "evaluated_setting_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": 18,
          "model": "openai/gpt-oss-120b",
          "point_rating_method": "sequential_elo",
          "public_id": "E-3a27113d21c73b01",
          "rated_matches": 46,
          "raw_elo_rating": 1413.6729432495829,
          "reasoning": "high",
          "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": 14.555454895164242,
          "uncertainty": 29.182495748947275,
          "unilateral_faults": 0,
          "wins": 6
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 46,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 23,
          "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": 14,
          "model": "tencent/hy3-preview",
          "point_rating_method": "sequential_elo",
          "public_id": "E-51c104b34ef2a244",
          "rated_matches": 46,
          "raw_elo_rating": 1441.0086683971886,
          "reasoning": "high",
          "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": 19.521885616164113,
          "uncertainty": 29.182495748947275,
          "unilateral_faults": 0,
          "wins": 6
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 44,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 22,
          "draws": 19,
          "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": 11,
          "model": "thinkingmachines/inkling",
          "point_rating_method": "sequential_elo",
          "public_id": "E-f130161523da1e6b",
          "rated_matches": 44,
          "raw_elo_rating": 1494.2033950634172,
          "reasoning": "max",
          "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": 28.95344674494225,
          "uncertainty": 30.785599249992988,
          "unilateral_faults": 0,
          "wins": 14
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 40,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 20,
          "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": "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-07caaa12175b0b3c",
          "rated_matches": 40,
          "raw_elo_rating": 1428.7678976898524,
          "reasoning": "high",
          "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": 16.548777830054647,
          "uncertainty": 34.33688094430304,
          "unilateral_faults": 0,
          "wins": 7
        },
        {
          "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": 1502.1064415265755,
          "reasoning": "high",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "repaired",
          "score": 32.47394764651104,
          "uncertainty": 16.4429265428846,
          "unilateral_faults": 0,
          "wins": 6
        }
      ],
      "GB2-05": [
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 98,
          "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-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": 98,
          "raw_elo_rating": 2007.5728572044336,
          "reasoning": "xhigh",
          "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": 90.25579059650316,
          "uncertainty": 6.501890762960602,
          "unilateral_faults": 0,
          "wins": 82
        },
        {
          "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": "legacy_shared_thinking_budget",
          "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": 54,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 27,
          "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": 26,
          "model": "claude-opus-4-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-ccacc93776fb7c88",
          "rated_matches": 54,
          "raw_elo_rating": 1464.860082832403,
          "reasoning": "high",
          "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": 37.739395426388306,
          "uncertainty": 23.66998624632421,
          "unilateral_faults": 0,
          "wins": 28
        },
        {
          "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": "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": 63,
          "model": "claude-opus-4-8",
          "point_rating_method": "sequential_elo",
          "public_id": "E-6774d700e60de31a",
          "rated_matches": 116,
          "raw_elo_rating": 1532.5443530487862,
          "reasoning": "xhigh",
          "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": 45.72757509137996,
          "uncertainty": 2.4750163521024238,
          "unilateral_faults": 0,
          "wins": 53
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 68,
          "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": 68,
          "raw_elo_rating": 2118.7722722673184,
          "reasoning": "xhigh",
          "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": 16.4429265428846,
          "unilateral_faults": 0,
          "wins": 68
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 68,
          "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": 68,
          "raw_elo_rating": 1805.196965973831,
          "reasoning": "xhigh",
          "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": 70.40538042295204,
          "uncertainty": 16.4429265428846,
          "unilateral_faults": 0,
          "wins": 46
        },
        {
          "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": "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": 44,
          "model": "deepseek/deepseek-v4-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-b3d889b0631db85f",
          "rated_matches": 96,
          "raw_elo_rating": 1559.7911348935588,
          "reasoning": "xhigh",
          "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": 47.95611862982329,
          "uncertainty": 7.017308256680951,
          "unilateral_faults": 0,
          "wins": 52
        },
        {
          "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-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": 96,
          "raw_elo_rating": 1805.1338387843662,
          "reasoning": "xhigh",
          "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": 71.11107962938964,
          "uncertainty": 7.017308256680951,
          "unilateral_faults": 0,
          "wins": 61
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 46,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 23,
          "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": 42,
          "model": "google/gemini-3.1-flash-lite",
          "point_rating_method": "sequential_elo",
          "public_id": "E-a72dd193e1dc4331",
          "rated_matches": 46,
          "raw_elo_rating": 1209.6423317720237,
          "reasoning": "high",
          "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": 13.23623910301927,
          "uncertainty": 29.182495748947275,
          "unilateral_faults": 0,
          "wins": 4
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 50,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 25,
          "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": 26,
          "model": "google/gemini-3.5-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-b50da126631c1ea1",
          "rated_matches": 50,
          "raw_elo_rating": 1459.949544325857,
          "reasoning": "high",
          "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": 37.08009383434464,
          "uncertainty": 26.264004201400486,
          "unilateral_faults": 0,
          "wins": 24
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 34,
          "capped_draws": 0,
          "coverage_status": "under_covered",
          "distinct_rated_opponents": 17,
          "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": 27,
          "model": "google/gemini-3.5-flash-lite",
          "point_rating_method": "sequential_elo",
          "public_id": "E-06abb3c93d2072c8",
          "rated_matches": 34,
          "raw_elo_rating": 1254.9687139277914,
          "reasoning": "high",
          "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": 16.63951447666021,
          "uncertainty": 40.76542547285167,
          "unilateral_faults": 0,
          "wins": 7
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 38,
          "capped_draws": 0,
          "coverage_status": "under_covered",
          "distinct_rated_opponents": 19,
          "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": 31,
          "model": "google/gemini-3.5-flash-lite",
          "point_rating_method": "sequential_elo",
          "public_id": "E-5b803013ec40d15d",
          "rated_matches": 38,
          "raw_elo_rating": 1237.5408240912482,
          "reasoning": "high",
          "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": 15.330792177830268,
          "uncertainty": 36.31407690254356,
          "unilateral_faults": 0,
          "wins": 7
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 30,
          "capped_draws": 0,
          "coverage_status": "under_covered",
          "distinct_rated_opponents": 15,
          "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
            "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-8b9ff59d79afb558",
          "rated_matches": 30,
          "raw_elo_rating": 1665.3032357357797,
          "reasoning": "high",
          "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": 54.96687982792465,
          "uncertainty": 46.05265101338746,
          "unilateral_faults": 0,
          "wins": 23
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 32,
          "capped_draws": 0,
          "coverage_status": "under_covered",
          "distinct_rated_opponents": 16,
          "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
            "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-c4f143aad203feb3",
          "rated_matches": 32,
          "raw_elo_rating": 1577.226054226596,
          "reasoning": "high",
          "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": 46.863004311807074,
          "uncertainty": 43.288827977848925,
          "unilateral_faults": 0,
          "wins": 18
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 48,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 24,
          "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": 21,
          "model": "gpt-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-c5ad048b6fb4e93d",
          "rated_matches": 48,
          "raw_elo_rating": 1609.7603755655746,
          "reasoning": "high",
          "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": 51.11214166332489,
          "uncertainty": 27.678571428571434,
          "unilateral_faults": 0,
          "wins": 27
        },
        {
          "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-5.4",
            "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": 92,
          "raw_elo_rating": 2032.5608459804337,
          "reasoning": "xhigh",
          "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": 92.49362898125582,
          "uncertainty": 8.09758473652126,
          "unilateral_faults": 0,
          "wins": 84
        },
        {
          "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": "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": 20,
          "model": "gpt-5.5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-762e9d80a60b41ed",
          "rated_matches": 96,
          "raw_elo_rating": 1913.7523653539108,
          "reasoning": "xhigh",
          "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": 81.36228215819001,
          "uncertainty": 7.017308256680951,
          "unilateral_faults": 0,
          "wins": 76
        },
        {
          "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": "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": 56,
          "model": "gpt-5.6-luna",
          "point_rating_method": "sequential_elo",
          "public_id": "E-25a83ddaeb1268a4",
          "rated_matches": 106,
          "raw_elo_rating": 1618.20016176997,
          "reasoning": "xhigh",
          "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": 53.65215492250481,
          "uncertainty": 4.586824452283178,
          "unilateral_faults": 0,
          "wins": 50
        },
        {
          "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-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": 33,
          "model": "gpt-5.6-sol",
          "point_rating_method": "sequential_elo",
          "public_id": "E-af9c2c2998294ad0",
          "rated_matches": 92,
          "raw_elo_rating": 1729.2371283141379,
          "reasoning": "xhigh",
          "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": 63.86653414034944,
          "uncertainty": 8.09758473652126,
          "unilateral_faults": 0,
          "wins": 59
        },
        {
          "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": "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": 94,
          "raw_elo_rating": 1649.9512272105483,
          "reasoning": "xhigh",
          "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": 56.425112707893895,
          "uncertainty": 7.54891760425771,
          "unilateral_faults": 0,
          "wins": 52
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 48,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 24,
          "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": 40,
          "model": "mistralai/mistral-medium-3-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-1954b83d439b455c",
          "rated_matches": 48,
          "raw_elo_rating": 1252.6537658690042,
          "reasoning": "high",
          "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": 17.40912343991944,
          "uncertainty": 27.678571428571434,
          "unilateral_faults": 0,
          "wins": 8
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 50,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 25,
          "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": 36,
          "model": "nvidia/nemotron-3-ultra-550b-a55b",
          "point_rating_method": "sequential_elo",
          "public_id": "E-48ed5c5e00ef38fb",
          "rated_matches": 50,
          "raw_elo_rating": 1365.1921728533348,
          "reasoning": "high",
          "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": 28.137079813254427,
          "uncertainty": 26.264004201400486,
          "unilateral_faults": 0,
          "wins": 14
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 50,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 25,
          "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": 31,
          "model": "nvidia/nemotron-3-ultra-550b-a55b",
          "point_rating_method": "sequential_elo",
          "public_id": "E-da3b98638ff53ea9",
          "rated_matches": 50,
          "raw_elo_rating": 1410.0340038022753,
          "reasoning": "high",
          "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": 32.36916346728466,
          "uncertainty": 26.264004201400486,
          "unilateral_faults": 0,
          "wins": 19
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 58,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 29,
          "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 28,
          "model": "o3",
          "point_rating_method": "sequential_elo",
          "public_id": "E-4724b57e861c4ecf",
          "rated_matches": 58,
          "raw_elo_rating": 1481.4182498230907,
          "reasoning": "high",
          "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": 39.47770581139428,
          "uncertainty": 21.344455490411935,
          "unilateral_faults": 0,
          "wins": 30
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 54,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 27,
          "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-03T16:00:00Z",
          "losses": 31,
          "model": "o3",
          "point_rating_method": "sequential_elo",
          "public_id": "E-61d05a26a332d2e5",
          "rated_matches": 54,
          "raw_elo_rating": 1477.2336049189955,
          "reasoning": "high",
          "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": 38.90718406162663,
          "uncertainty": 23.66998624632421,
          "unilateral_faults": 0,
          "wins": 23
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 32,
          "capped_draws": 0,
          "coverage_status": "under_covered",
          "distinct_rated_opponents": 16,
          "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-03T15:45:00Z",
          "losses": 17,
          "model": "o3",
          "point_rating_method": "sequential_elo",
          "public_id": "E-9bfe5e29476019eb",
          "rated_matches": 32,
          "raw_elo_rating": 1440.366983423129,
          "reasoning": "high",
          "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": 33.94651485996851,
          "uncertainty": 43.288827977848925,
          "unilateral_faults": 0,
          "wins": 15
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 34,
          "capped_draws": 0,
          "coverage_status": "under_covered",
          "distinct_rated_opponents": 17,
          "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-03T15:50:00Z",
          "losses": 17,
          "model": "o3",
          "point_rating_method": "sequential_elo",
          "public_id": "E-ffb183b7ecfe85e0",
          "rated_matches": 34,
          "raw_elo_rating": 1447.7539890513212,
          "reasoning": "high",
          "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": 34.83420890198426,
          "uncertainty": 40.76542547285167,
          "unilateral_faults": 0,
          "wins": 17
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 50,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 25,
          "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": 27,
          "model": "stepfun/step-3.7-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-358338a9fbdbcb6a",
          "rated_matches": 50,
          "raw_elo_rating": 1483.1982568705898,
          "reasoning": "high",
          "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": 39.274261517859706,
          "uncertainty": 26.264004201400486,
          "unilateral_faults": 0,
          "wins": 23
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 48,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 24,
          "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": 25,
          "model": "tencent/hy3-preview",
          "point_rating_method": "sequential_elo",
          "public_id": "E-92dc0ac61d798488",
          "rated_matches": 48,
          "raw_elo_rating": 1472.1934264239376,
          "reasoning": "high",
          "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": 38.12884404864786,
          "uncertainty": 27.678571428571434,
          "unilateral_faults": 0,
          "wins": 23
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 34,
          "capped_draws": 0,
          "coverage_status": "under_covered",
          "distinct_rated_opponents": 17,
          "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": 30,
          "model": "thinkingmachines/inkling",
          "point_rating_method": "sequential_elo",
          "public_id": "E-2c483dc32fc18ba8",
          "rated_matches": 34,
          "raw_elo_rating": 1189.998924181859,
          "reasoning": "max",
          "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": 10.50779372907021,
          "uncertainty": 40.76542547285167,
          "unilateral_faults": 0,
          "wins": 4
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 36,
          "capped_draws": 0,
          "coverage_status": "under_covered",
          "distinct_rated_opponents": 18,
          "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": 27,
          "model": "thinkingmachines/inkling",
          "point_rating_method": "sequential_elo",
          "public_id": "E-e9202aa1565d1c4e",
          "rated_matches": 36,
          "raw_elo_rating": 1291.2455175290106,
          "reasoning": "max",
          "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": 20.238106190832827,
          "uncertainty": 38.449493652678655,
          "unilateral_faults": 0,
          "wins": 9
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 34,
          "capped_draws": 0,
          "coverage_status": "under_covered",
          "distinct_rated_opponents": 17,
          "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": 18,
          "model": "x-ai/grok-4.5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-8e6cb252293b2af9",
          "rated_matches": 34,
          "raw_elo_rating": 1577.57790394916,
          "reasoning": "high",
          "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": 47.08673420067161,
          "uncertainty": 40.76542547285167,
          "unilateral_faults": 0,
          "wins": 16
        }
      ],
      "GB2-06": [
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 82,
          "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": 82,
          "raw_elo_rating": 1877.949290834117,
          "reasoning": "xhigh",
          "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": 93.83172258846857,
          "uncertainty": 11.132129994845172,
          "unilateral_faults": 0,
          "wins": 63
        },
        {
          "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": "legacy_shared_thinking_budget",
          "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": 54,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 27,
          "draws": 5,
          "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": 25,
          "model": "claude-opus-4-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-df9bde92610963b7",
          "rated_matches": 54,
          "raw_elo_rating": 1524.5109055238481,
          "reasoning": "high",
          "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": 55.16444931458042,
          "uncertainty": 23.66998624632421,
          "unilateral_faults": 0,
          "wins": 24
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 80,
          "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": 16,
          "model": "claude-opus-4-8",
          "point_rating_method": "sequential_elo",
          "public_id": "E-e804041031295d93",
          "rated_matches": 80,
          "raw_elo_rating": 1802.081054869981,
          "reasoning": "xhigh",
          "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": 85.7032381321606,
          "uncertainty": 11.805555555555554,
          "unilateral_faults": 0,
          "wins": 62
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 82,
          "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": 57,
          "model": "deepseek/deepseek-v4-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-5f5fd61f4544b8d7",
          "rated_matches": 82,
          "raw_elo_rating": 1301.2737990682394,
          "reasoning": "xhigh",
          "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": 32.48264176849661,
          "uncertainty": 11.132129994845172,
          "unilateral_faults": 0,
          "wins": 24
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 114,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 56,
          "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": 61,
          "model": "deepseek/deepseek-v4-pro",
          "point_rating_method": "sequential_elo",
          "public_id": "E-c9778645f1bbd12c",
          "rated_matches": 114,
          "raw_elo_rating": 1418.5606086737382,
          "reasoning": "xhigh",
          "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": 45.6628100593333,
          "uncertainty": 2.875240412015687,
          "unilateral_faults": 0,
          "wins": 51
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 45,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 23,
          "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": 39,
          "model": "google/gemini-3.1-flash-lite",
          "point_rating_method": "sequential_elo",
          "public_id": "E-6238c7d8dc9e77d9",
          "rated_matches": 45,
          "raw_elo_rating": 1254.5543630538143,
          "reasoning": "high",
          "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": 25.909115893200116,
          "uncertainty": 29.97097807744857,
          "unilateral_faults": 0,
          "wins": 6
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 42,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 21,
          "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": "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-5dcb27eaa0273049",
          "rated_matches": 42,
          "raw_elo_rating": 1667.9573138611443,
          "reasoning": "high",
          "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": 69.67342345942932,
          "uncertainty": 32.49928516630233,
          "unilateral_faults": 0,
          "wins": 29
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 28,
          "capped_draws": 0,
          "coverage_status": "under_covered",
          "distinct_rated_opponents": 14,
          "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": 17,
          "model": "google/gemini-3.5-flash-lite",
          "point_rating_method": "sequential_elo",
          "public_id": "E-09a450a1726f909a",
          "rated_matches": 28,
          "raw_elo_rating": 1385.6245012441173,
          "reasoning": "high",
          "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": 38.22506944455974,
          "uncertainty": 49.09766908852594,
          "unilateral_faults": 0,
          "wins": 11
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 24,
          "capped_draws": 0,
          "coverage_status": "under_covered",
          "distinct_rated_opponents": 12,
          "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-3.5-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": 11,
          "model": "google/gemini-3.5-flash-lite",
          "point_rating_method": "sequential_elo",
          "public_id": "E-48cc2611d5aa8816",
          "rated_matches": 24,
          "raw_elo_rating": 1527.0659614938158,
          "reasoning": "high",
          "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": 52.663471203139416,
          "uncertainty": 56.25,
          "unilateral_faults": 0,
          "wins": 11
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 42,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 21,
          "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": "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-280a7de63c992141",
          "rated_matches": 42,
          "raw_elo_rating": 1599.9788656538626,
          "reasoning": "high",
          "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": 62.44160006371974,
          "uncertainty": 32.49928516630233,
          "unilateral_faults": 0,
          "wins": 25
        },
        {
          "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": "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": 3,
          "model": "google/gemini-3.6-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-905531e52a8460f5",
          "rated_matches": 22,
          "raw_elo_rating": 1732.197709542942,
          "reasoning": "high",
          "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": 74.12390046720022,
          "uncertainty": 60.5072070285374,
          "unilateral_faults": 0,
          "wins": 19
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 46,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 23,
          "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": "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": 11,
          "model": "gpt-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-1b082700b3692175",
          "rated_matches": 46,
          "raw_elo_rating": 1686.2801409522417,
          "reasoning": "high",
          "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": 71.90496304115143,
          "uncertainty": 29.182495748947275,
          "unilateral_faults": 0,
          "wins": 31
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 82,
          "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-5.4",
            "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": 82,
          "raw_elo_rating": 1935.9305085166034,
          "reasoning": "xhigh",
          "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": 11.132129994845172,
          "unilateral_faults": 0,
          "wins": 65
        },
        {
          "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": "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": 82,
          "raw_elo_rating": 1880.0797890873182,
          "reasoning": "xhigh",
          "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": 94.05837364506577,
          "uncertainty": 11.132129994845172,
          "unilateral_faults": 0,
          "wins": 62
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 84,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 40,
          "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": 84,
          "raw_elo_rating": 1757.888067823131,
          "reasoning": "xhigh",
          "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": 81.11440057033718,
          "uncertainty": 10.482614454664043,
          "unilateral_faults": 0,
          "wins": 52
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 84,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 39,
          "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": 84,
          "raw_elo_rating": 1786.9238690390182,
          "reasoning": "xhigh",
          "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": 84.20334702445369,
          "uncertainty": 10.482614454664043,
          "unilateral_faults": 0,
          "wins": 58
        },
        {
          "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-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": 90,
          "raw_elo_rating": 1736.344551427424,
          "reasoning": "xhigh",
          "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": 78.97727049438612,
          "uncertainty": 8.664241836095918,
          "unilateral_faults": 0,
          "wins": 56
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 46,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 23,
          "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": 39,
          "model": "mistralai/mistral-medium-3-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-6c35f5ff426e7ada",
          "rated_matches": 46,
          "raw_elo_rating": 1265.0878617129324,
          "reasoning": "high",
          "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": 27.096817821255087,
          "uncertainty": 29.182495748947275,
          "unilateral_faults": 0,
          "wins": 7
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 49,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 25,
          "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": "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": 35,
          "model": "nvidia/nemotron-3-ultra-550b-a55b",
          "point_rating_method": "sequential_elo",
          "public_id": "E-ba2fb1c121873708",
          "rated_matches": 49,
          "raw_elo_rating": 1320.5027486009951,
          "reasoning": "high",
          "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": 33.181171326682524,
          "uncertainty": 26.960678118654744,
          "unilateral_faults": 0,
          "wins": 12
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 30,
          "capped_draws": 0,
          "coverage_status": "under_covered",
          "distinct_rated_opponents": 15,
          "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-03T16:00:00Z",
          "losses": 15,
          "model": "o3",
          "point_rating_method": "sequential_elo",
          "public_id": "E-2c94ff7a30958259",
          "rated_matches": 30,
          "raw_elo_rating": 1473.6395745244195,
          "reasoning": "high",
          "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": 47.84762350013217,
          "uncertainty": 46.05265101338746,
          "unilateral_faults": 0,
          "wins": 15
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 30,
          "capped_draws": 0,
          "coverage_status": "under_covered",
          "distinct_rated_opponents": 15,
          "draws": 2,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "o3",
            "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-03T15:50:00Z",
          "losses": 17,
          "model": "o3",
          "point_rating_method": "sequential_elo",
          "public_id": "E-35751e26cd4e995d",
          "rated_matches": 30,
          "raw_elo_rating": 1409.2273088877162,
          "reasoning": "high",
          "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": 40.99518508933194,
          "uncertainty": 46.05265101338746,
          "unilateral_faults": 0,
          "wins": 11
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 30,
          "capped_draws": 0,
          "coverage_status": "under_covered",
          "distinct_rated_opponents": 15,
          "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 21,
          "model": "o3",
          "point_rating_method": "sequential_elo",
          "public_id": "E-432424671c9fea1c",
          "rated_matches": 30,
          "raw_elo_rating": 1346.2478156014672,
          "reasoning": "high",
          "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": 34.29517081997646,
          "uncertainty": 46.05265101338746,
          "unilateral_faults": 0,
          "wins": 9
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 28,
          "capped_draws": 0,
          "coverage_status": "under_covered",
          "distinct_rated_opponents": 14,
          "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-03T15:45:00Z",
          "losses": 14,
          "model": "o3",
          "point_rating_method": "sequential_elo",
          "public_id": "E-ead4229a85e5d554",
          "rated_matches": 28,
          "raw_elo_rating": 1478.8537747463809,
          "reasoning": "high",
          "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": 48.14317818430083,
          "uncertainty": 49.09766908852594,
          "unilateral_faults": 0,
          "wins": 13
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 50,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 25,
          "draws": 4,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "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": 18,
          "model": "openai/gpt-oss-120b",
          "point_rating_method": "sequential_elo",
          "public_id": "E-a97b527d9b41a80c",
          "rated_matches": 50,
          "raw_elo_rating": 1619.371511306429,
          "reasoning": "high",
          "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": 65.03533607555016,
          "uncertainty": 26.264004201400486,
          "unilateral_faults": 0,
          "wins": 28
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 50,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 25,
          "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": "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": 39,
          "model": "stepfun/step-3.7-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-2d684425ca56be18",
          "rated_matches": 50,
          "raw_elo_rating": 1316.16547310662,
          "reasoning": "high",
          "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": 32.779046345492574,
          "uncertainty": 26.264004201400486,
          "unilateral_faults": 0,
          "wins": 10
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 42,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 21,
          "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": 36,
          "model": "tencent/hy3-preview",
          "point_rating_method": "sequential_elo",
          "public_id": "E-3627e3dbf7a48738",
          "rated_matches": 42,
          "raw_elo_rating": 1269.8921642421287,
          "reasoning": "high",
          "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": 27.325636212896253,
          "uncertainty": 32.49928516630233,
          "unilateral_faults": 0,
          "wins": 6
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 26,
          "capped_draws": 0,
          "coverage_status": "under_covered",
          "distinct_rated_opponents": 13,
          "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": 12,
          "model": "thinkingmachines/inkling",
          "point_rating_method": "sequential_elo",
          "public_id": "E-56e54327930d2f64",
          "rated_matches": 26,
          "raw_elo_rating": 1513.8216182614226,
          "reasoning": "max",
          "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": 51.575760228440956,
          "uncertainty": 52.475044864937615,
          "unilateral_faults": 0,
          "wins": 14
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 44,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 22,
          "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": "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": 22,
          "model": "x-ai/grok-4.5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-5a1e23bce371a184",
          "rated_matches": 44,
          "raw_elo_rating": 1503.5914373587705,
          "reasoning": "high",
          "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": 52.33336108510253,
          "uncertainty": 30.785599249992988,
          "unilateral_faults": 0,
          "wins": 19
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 68,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 34,
          "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": "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": 28,
          "model": "xiaomi/mimo-v2.5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-51421c7ae2af8f7b",
          "rated_matches": 68,
          "raw_elo_rating": 1588.8776884828033,
          "reasoning": "high",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "repaired",
          "score": 62.62712426295049,
          "uncertainty": 16.4429265428846,
          "unilateral_faults": 0,
          "wins": 34
        }
      ],
      "GB2-07": [
        {
          "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": "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": 90,
          "raw_elo_rating": 1713.9112383774284,
          "reasoning": "xhigh",
          "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": 66.9670189086873,
          "uncertainty": 8.664241836095918,
          "unilateral_faults": 0,
          "wins": 55
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 50,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 25,
          "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": 28,
          "model": "claude-opus-4-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-e8719bed57f17312",
          "rated_matches": 50,
          "raw_elo_rating": 1450.1460873197461,
          "reasoning": "high",
          "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": 39.29831320648614,
          "uncertainty": 26.264004201400486,
          "unilateral_faults": 0,
          "wins": 22
        },
        {
          "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": "legacy_shared_thinking_budget",
          "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": 90,
          "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-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": 90,
          "raw_elo_rating": 1803.2582355928973,
          "reasoning": "xhigh",
          "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": 75.86448374979243,
          "uncertainty": 8.664241836095918,
          "unilateral_faults": 0,
          "wins": 69
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 78,
          "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": 78,
          "raw_elo_rating": 2048.6955646228785,
          "reasoning": "xhigh",
          "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": 12.5043950463012,
          "unilateral_faults": 0,
          "wins": 77
        },
        {
          "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": "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-ecf2a6ea6f9fe06c",
          "rated_matches": 92,
          "raw_elo_rating": 1741.0405753174614,
          "reasoning": "xhigh",
          "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": 69.71379024439247,
          "uncertainty": 8.09758473652126,
          "unilateral_faults": 0,
          "wins": 63
        },
        {
          "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": "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": 52,
          "model": "deepseek/deepseek-v4-pro",
          "point_rating_method": "sequential_elo",
          "public_id": "E-f398fd6ac8c8bada",
          "rated_matches": 96,
          "raw_elo_rating": 1592.3030320455705,
          "reasoning": "xhigh",
          "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": 54.98808344707694,
          "uncertainty": 7.017308256680951,
          "unilateral_faults": 0,
          "wins": 44
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 50,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 25,
          "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": 39,
          "model": "google/gemini-3.1-flash-lite",
          "point_rating_method": "sequential_elo",
          "public_id": "E-0d43f308cfa4da52",
          "rated_matches": 50,
          "raw_elo_rating": 1334.9311531054598,
          "reasoning": "high",
          "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": 27.824834989085325,
          "uncertainty": 26.264004201400486,
          "unilateral_faults": 0,
          "wins": 11
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 46,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 23,
          "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": 19,
          "model": "google/gemini-3.5-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-f7f306cca2bb9532",
          "rated_matches": 46,
          "raw_elo_rating": 1614.5960622689374,
          "reasoning": "high",
          "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": 55.44227074773221,
          "uncertainty": 29.182495748947275,
          "unilateral_faults": 0,
          "wins": 27
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 40,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 20,
          "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": 26,
          "model": "google/gemini-3.5-flash-lite",
          "point_rating_method": "sequential_elo",
          "public_id": "E-c4d27e5c752afb39",
          "rated_matches": 40,
          "raw_elo_rating": 1422.0317210539686,
          "reasoning": "high",
          "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": 35.85545441373769,
          "uncertainty": 34.33688094430304,
          "unilateral_faults": 0,
          "wins": 14
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 44,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 22,
          "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": 28,
          "model": "google/gemini-3.5-flash-lite",
          "point_rating_method": "sequential_elo",
          "public_id": "E-f746ec3aee7874b2",
          "rated_matches": 44,
          "raw_elo_rating": 1420.1759752219925,
          "reasoning": "high",
          "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": 35.95357175614385,
          "uncertainty": 30.785599249992988,
          "unilateral_faults": 0,
          "wins": 16
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 47,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 24,
          "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": 24,
          "model": "google/gemini-3.6-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-f6ecc1626f38fa34",
          "rated_matches": 47,
          "raw_elo_rating": 1535.5674257043515,
          "reasoning": "high",
          "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": 47.63318420011444,
          "uncertainty": 28.418783648703226,
          "unilateral_faults": 0,
          "wins": 23
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 54,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 27,
          "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": 28,
          "model": "gpt-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-15dad0db253c0497",
          "rated_matches": 54,
          "raw_elo_rating": 1511.696585516207,
          "reasoning": "high",
          "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": 45.63436878910724,
          "uncertainty": 23.66998624632421,
          "unilateral_faults": 0,
          "wins": 26
        },
        {
          "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-5.4",
            "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": 96,
          "raw_elo_rating": 1934.857523033671,
          "reasoning": "xhigh",
          "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": 89.10077480456111,
          "uncertainty": 7.017308256680951,
          "unilateral_faults": 0,
          "wins": 85
        },
        {
          "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": "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": 96,
          "raw_elo_rating": 1964.5526124609985,
          "reasoning": "xhigh",
          "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": 92.05790847852163,
          "uncertainty": 7.017308256680951,
          "unilateral_faults": 0,
          "wins": 90
        },
        {
          "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-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": 28,
          "model": "gpt-5.6-luna",
          "point_rating_method": "sequential_elo",
          "public_id": "E-73a7b73c1df452ad",
          "rated_matches": 92,
          "raw_elo_rating": 1808.0596113105762,
          "reasoning": "xhigh",
          "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": 76.38776402098694,
          "uncertainty": 8.09758473652126,
          "unilateral_faults": 0,
          "wins": 64
        },
        {
          "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": "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": 29,
          "model": "gpt-5.6-sol",
          "point_rating_method": "sequential_elo",
          "public_id": "E-1b522c9c14f3860c",
          "rated_matches": 92,
          "raw_elo_rating": 1633.041024252725,
          "reasoning": "xhigh",
          "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": 58.95884336983468,
          "uncertainty": 8.09758473652126,
          "unilateral_faults": 0,
          "wins": 63
        },
        {
          "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": "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": 92,
          "raw_elo_rating": 1761.1968899835726,
          "reasoning": "xhigh",
          "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": 71.72102167529864,
          "uncertainty": 8.09758473652126,
          "unilateral_faults": 0,
          "wins": 63
        },
        {
          "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": "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": 50,
          "model": "mistralai/mistral-medium-3-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-d0d0df9d83b6e37e",
          "rated_matches": 52,
          "raw_elo_rating": 1166.352764344129,
          "reasoning": "high",
          "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": 11.143503370504328,
          "uncertainty": 24.930281974344517,
          "unilateral_faults": 0,
          "wins": 2
        },
        {
          "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": "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": 22,
          "model": "moonshotai/kimi-k3",
          "point_rating_method": "sequential_elo",
          "public_id": "E-1d1372c78963efdf",
          "rated_matches": 52,
          "raw_elo_rating": 1621.2324506288412,
          "reasoning": "max",
          "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": 56.441903336770274,
          "uncertainty": 24.930281974344517,
          "unilateral_faults": 0,
          "wins": 30
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 46,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 23,
          "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-03T15:50:00Z",
          "losses": 29,
          "model": "o3",
          "point_rating_method": "sequential_elo",
          "public_id": "E-43c337fb7f5e535e",
          "rated_matches": 46,
          "raw_elo_rating": 1441.898196137617,
          "reasoning": "high",
          "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": 38.24445504127137,
          "uncertainty": 29.182495748947275,
          "unilateral_faults": 0,
          "wins": 17
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 44,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 22,
          "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-03T15:45:00Z",
          "losses": 28,
          "model": "o3",
          "point_rating_method": "sequential_elo",
          "public_id": "E-541cee4461c65fcb",
          "rated_matches": 44,
          "raw_elo_rating": 1400.2873857932564,
          "reasoning": "high",
          "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": 33.97300127592274,
          "uncertainty": 30.785599249992988,
          "unilateral_faults": 0,
          "wins": 16
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 46,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 23,
          "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 26,
          "model": "o3",
          "point_rating_method": "sequential_elo",
          "public_id": "E-bc20ac8102f6a0ac",
          "rated_matches": 46,
          "raw_elo_rating": 1488.5445965948081,
          "reasoning": "high",
          "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": 42.889655450537184,
          "uncertainty": 29.182495748947275,
          "unilateral_faults": 0,
          "wins": 20
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 50,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 25,
          "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-03T16:00:00Z",
          "losses": 40,
          "model": "o3",
          "point_rating_method": "sequential_elo",
          "public_id": "E-ee95d01578313864",
          "rated_matches": 50,
          "raw_elo_rating": 1313.573763760422,
          "reasoning": "high",
          "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": 25.697996631697677,
          "uncertainty": 26.264004201400486,
          "unilateral_faults": 0,
          "wins": 10
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 50,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 25,
          "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": 39,
          "model": "openai/gpt-oss-120b",
          "point_rating_method": "sequential_elo",
          "public_id": "E-29bc7f4fdf0f7b14",
          "rated_matches": 50,
          "raw_elo_rating": 1310.7089917355493,
          "reasoning": "high",
          "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": 25.412713307540546,
          "uncertainty": 26.264004201400486,
          "unilateral_faults": 0,
          "wins": 11
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 53,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 27,
          "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": 43,
          "model": "stepfun/step-3.7-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-6a5e44fe2dde4257",
          "rated_matches": 53,
          "raw_elo_rating": 1261.8941078649368,
          "reasoning": "high",
          "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": 20.708720393485684,
          "uncertainty": 24.291381743977166,
          "unilateral_faults": 0,
          "wins": 10
        },
        {
          "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": "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": 44,
          "model": "tencent/hy3-preview",
          "point_rating_method": "sequential_elo",
          "public_id": "E-dfed1e345a939bcd",
          "rated_matches": 52,
          "raw_elo_rating": 1237.7335607826108,
          "reasoning": "high",
          "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": 18.25183545143426,
          "uncertainty": 24.930281974344517,
          "unilateral_faults": 0,
          "wins": 8
        },
        {
          "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": "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": 44,
          "model": "thinkingmachines/inkling",
          "point_rating_method": "sequential_elo",
          "public_id": "E-38e756fc6f3a2db6",
          "rated_matches": 52,
          "raw_elo_rating": 1260.0528626269393,
          "reasoning": "max",
          "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": 20.47446418689157,
          "uncertainty": 24.930281974344517,
          "unilateral_faults": 0,
          "wins": 8
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 44,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 22,
          "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": 18,
          "model": "x-ai/grok-4.5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-436a3933a93e10cd",
          "rated_matches": 44,
          "raw_elo_rating": 1628.7660671784279,
          "reasoning": "high",
          "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": 56.72565215308805,
          "uncertainty": 30.785599249992988,
          "unilateral_faults": 0,
          "wins": 26
        }
      ],
      "GB2-08": [
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 100,
          "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": 100,
          "raw_elo_rating": 2047.0897119000806,
          "reasoning": "xhigh",
          "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": 6.001859510499461,
          "unilateral_faults": 0,
          "wins": 95
        },
        {
          "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": "legacy_shared_thinking_budget",
          "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": 50,
          "capped_draws": 24,
          "coverage_status": "rated",
          "distinct_rated_opponents": 25,
          "draws": 24,
          "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": 20,
          "model": "claude-opus-4-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-877eec51affacb3a",
          "rated_matches": 50,
          "raw_elo_rating": 1422.5591374636776,
          "reasoning": "high",
          "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": 24.02309284446473,
          "uncertainty": 26.264004201400486,
          "unilateral_faults": 0,
          "wins": 6
        },
        {
          "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": "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": 96,
          "raw_elo_rating": 1769.8005525842925,
          "reasoning": "xhigh",
          "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": 67.02362320555288,
          "uncertainty": 7.017308256680951,
          "unilateral_faults": 0,
          "wins": 73
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 84,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 38,
          "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": 84,
          "raw_elo_rating": 1865.096194166436,
          "reasoning": "xhigh",
          "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": 77.99474773546663,
          "uncertainty": 10.482614454664043,
          "unilateral_faults": 0,
          "wins": 71
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 86,
          "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": 86,
          "raw_elo_rating": 1687.0626479500045,
          "reasoning": "xhigh",
          "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": 56.9435837175424,
          "uncertainty": 9.855626741889738,
          "unilateral_faults": 0,
          "wins": 60
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 104,
          "capped_draws": 73,
          "coverage_status": "rated",
          "distinct_rated_opponents": 52,
          "draws": 73,
          "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": 104,
          "raw_elo_rating": 1410.422225981586,
          "reasoning": "xhigh",
          "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": 24.5968014699668,
          "uncertainty": 5.045003647426665,
          "unilateral_faults": 0,
          "wins": 2
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 88,
          "capped_draws": 59,
          "coverage_status": "rated",
          "distinct_rated_opponents": 43,
          "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-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": 88,
          "raw_elo_rating": 1405.469355363088,
          "reasoning": "xhigh",
          "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": 23.61062430589122,
          "uncertainty": 9.249894000318006,
          "unilateral_faults": 0,
          "wins": 4
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 54,
          "capped_draws": 27,
          "coverage_status": "rated",
          "distinct_rated_opponents": 27,
          "draws": 27,
          "evaluated_setting_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": 25,
          "model": "google/gemini-3.1-flash-lite",
          "point_rating_method": "sequential_elo",
          "public_id": "E-b335c9f92035f80b",
          "rated_matches": 54,
          "raw_elo_rating": 1352.224951324873,
          "reasoning": "high",
          "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": 15.929165179121178,
          "uncertainty": 23.66998624632421,
          "unilateral_faults": 0,
          "wins": 2
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 54,
          "capped_draws": 26,
          "coverage_status": "rated",
          "distinct_rated_opponents": 27,
          "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": "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": 28,
          "model": "google/gemini-3.5-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-fa332e578ae97122",
          "rated_matches": 54,
          "raw_elo_rating": 1302.1407704231513,
          "reasoning": "high",
          "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": 9.990345316227936,
          "uncertainty": 23.66998624632421,
          "unilateral_faults": 0,
          "wins": 0
        },
        {
          "admitted_plugin_count": 2,
          "attempted_matches": 52,
          "capped_draws": 28,
          "coverage_status": "rated",
          "distinct_rated_opponents": 26,
          "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": 23,
          "model": "google/gemini-3.5-flash-lite",
          "point_rating_method": "sequential_elo",
          "public_id": "E-2a14d2f80ade1bda",
          "rated_matches": 52,
          "raw_elo_rating": 1351.1408038338798,
          "reasoning": "high",
          "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": 15.681057056511584,
          "uncertainty": 24.930281974344517,
          "unilateral_faults": 0,
          "wins": 1
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 52,
          "capped_draws": 8,
          "coverage_status": "rated",
          "distinct_rated_opponents": 26,
          "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": "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-620b5ca2bcd82419",
          "rated_matches": 52,
          "raw_elo_rating": 1676.6846736132431,
          "reasoning": "high",
          "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": 54.28299414084854,
          "uncertainty": 24.930281974344517,
          "unilateral_faults": 0,
          "wins": 34
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 46,
          "capped_draws": 23,
          "coverage_status": "rated",
          "distinct_rated_opponents": 23,
          "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-3.6-flash",
            "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 20,
          "model": "google/gemini-3.6-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-efad9f3f4e9183a0",
          "rated_matches": 46,
          "raw_elo_rating": 1379.2854789302758,
          "reasoning": "high",
          "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": 18.614990437288874,
          "uncertainty": 29.182495748947275,
          "unilateral_faults": 0,
          "wins": 3
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 54,
          "capped_draws": 25,
          "coverage_status": "rated",
          "distinct_rated_opponents": 27,
          "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": "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": 23,
          "model": "gpt-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-ebca8ea756b4a4ad",
          "rated_matches": 54,
          "raw_elo_rating": 1381.3649590509233,
          "reasoning": "high",
          "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": 19.384492860887867,
          "uncertainty": 23.66998624632421,
          "unilateral_faults": 0,
          "wins": 6
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 100,
          "capped_draws": 26,
          "coverage_status": "rated",
          "distinct_rated_opponents": 47,
          "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": 100,
          "raw_elo_rating": 1602.560257343934,
          "reasoning": "xhigh",
          "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": 47.28913787090833,
          "uncertainty": 6.001859510499461,
          "unilateral_faults": 0,
          "wins": 43
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 102,
          "capped_draws": 16,
          "coverage_status": "rated",
          "distinct_rated_opponents": 46,
          "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": 102,
          "raw_elo_rating": 1783.5389156654253,
          "reasoning": "xhigh",
          "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": 68.79504598485697,
          "uncertainty": 5.516463908214657,
          "unilateral_faults": 0,
          "wins": 62
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 92,
          "capped_draws": 6,
          "coverage_status": "rated",
          "distinct_rated_opponents": 45,
          "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-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": 92,
          "raw_elo_rating": 1645.1650048305432,
          "reasoning": "xhigh",
          "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": 52.14226731360425,
          "uncertainty": 8.09758473652126,
          "unilateral_faults": 0,
          "wins": 55
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 84,
          "capped_draws": 12,
          "coverage_status": "rated",
          "distinct_rated_opponents": 42,
          "draws": 12,
          "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": 50,
          "model": "gpt-5.6-sol",
          "point_rating_method": "sequential_elo",
          "public_id": "E-3ae62f195160add3",
          "rated_matches": 84,
          "raw_elo_rating": 1378.8902558829477,
          "reasoning": "xhigh",
          "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": 20.34202322749009,
          "uncertainty": 10.482614454664043,
          "unilateral_faults": 0,
          "wins": 22
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 98,
          "capped_draws": 15,
          "coverage_status": "rated",
          "distinct_rated_opponents": 46,
          "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": 32,
          "model": "gpt-5.6-terra",
          "point_rating_method": "sequential_elo",
          "public_id": "E-b061663dc342c859",
          "rated_matches": 98,
          "raw_elo_rating": 1615.127256233949,
          "reasoning": "xhigh",
          "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": 48.731858204888034,
          "uncertainty": 6.501890762960602,
          "unilateral_faults": 0,
          "wins": 51
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 54,
          "capped_draws": 27,
          "coverage_status": "rated",
          "distinct_rated_opponents": 27,
          "draws": 27,
          "evaluated_setting_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": 23,
          "model": "nvidia/nemotron-3-ultra-550b-a55b",
          "point_rating_method": "sequential_elo",
          "public_id": "E-2e3c01d0103fc439",
          "rated_matches": 54,
          "raw_elo_rating": 1363.9872394644565,
          "reasoning": "high",
          "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": 17.323899188518354,
          "uncertainty": 23.66998624632421,
          "unilateral_faults": 0,
          "wins": 4
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 54,
          "capped_draws": 27,
          "coverage_status": "rated",
          "distinct_rated_opponents": 27,
          "draws": 27,
          "evaluated_setting_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": 54,
          "raw_elo_rating": 1362.0074927001401,
          "reasoning": "high",
          "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": 17.089147232995877,
          "uncertainty": 23.66998624632421,
          "unilateral_faults": 0,
          "wins": 4
        },
        {
          "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": "openai",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "o3",
            "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-03T16:00:00Z",
          "losses": 11,
          "model": "o3",
          "point_rating_method": "sequential_elo",
          "public_id": "E-2270b9df7d2b32cc",
          "rated_matches": 52,
          "raw_elo_rating": 1743.8525025680906,
          "reasoning": "high",
          "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": 62.247537626689,
          "uncertainty": 24.930281974344517,
          "unilateral_faults": 0,
          "wins": 41
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 52,
          "capped_draws": 29,
          "coverage_status": "rated",
          "distinct_rated_opponents": 26,
          "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": "o3",
            "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-03T15:45:00Z",
          "losses": 21,
          "model": "o3",
          "point_rating_method": "sequential_elo",
          "public_id": "E-9fbb8e6c69f575f4",
          "rated_matches": 52,
          "raw_elo_rating": 1344.1624701054743,
          "reasoning": "high",
          "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": 14.85358885777086,
          "uncertainty": 24.930281974344517,
          "unilateral_faults": 0,
          "wins": 2
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 52,
          "capped_draws": 27,
          "coverage_status": "rated",
          "distinct_rated_opponents": 26,
          "draws": 27,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "o3",
            "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 21,
          "model": "o3",
          "point_rating_method": "sequential_elo",
          "public_id": "E-afa6c09eebc859c4",
          "rated_matches": 52,
          "raw_elo_rating": 1383.3495651097662,
          "reasoning": "high",
          "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": 19.500267589269747,
          "uncertainty": 24.930281974344517,
          "unilateral_faults": 0,
          "wins": 4
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 54,
          "capped_draws": 29,
          "coverage_status": "rated",
          "distinct_rated_opponents": 27,
          "draws": 29,
          "evaluated_setting_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": 54,
          "raw_elo_rating": 1357.5269587677542,
          "reasoning": "high",
          "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": 16.55786003941604,
          "uncertainty": 23.66998624632421,
          "unilateral_faults": 0,
          "wins": 3
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 54,
          "capped_draws": 32,
          "coverage_status": "rated",
          "distinct_rated_opponents": 27,
          "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": "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": 54,
          "raw_elo_rating": 1364.6824009874317,
          "reasoning": "high",
          "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": 17.406329189094095,
          "uncertainty": 23.66998624632421,
          "unilateral_faults": 0,
          "wins": 1
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 54,
          "capped_draws": 12,
          "coverage_status": "rated",
          "distinct_rated_opponents": 27,
          "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": "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": 24,
          "model": "tencent/hy3-preview",
          "point_rating_method": "sequential_elo",
          "public_id": "E-81a5e5ef15f371dc",
          "rated_matches": 54,
          "raw_elo_rating": 1457.1845022400166,
          "reasoning": "high",
          "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": 28.37492858290644,
          "uncertainty": 23.66998624632421,
          "unilateral_faults": 0,
          "wins": 18
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 54,
          "capped_draws": 24,
          "coverage_status": "rated",
          "distinct_rated_opponents": 27,
          "draws": 24,
          "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": 28,
          "model": "thinkingmachines/inkling",
          "point_rating_method": "sequential_elo",
          "public_id": "E-d21921560d198b28",
          "rated_matches": 54,
          "raw_elo_rating": 1333.1838510286977,
          "reasoning": "max",
          "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": 13.67133321273315,
          "uncertainty": 23.66998624632421,
          "unilateral_faults": 0,
          "wins": 2
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 48,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 24,
          "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": 6,
          "model": "x-ai/grok-4.5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-707dd709e358a173",
          "rated_matches": 48,
          "raw_elo_rating": 1799.9643985417936,
          "reasoning": "high",
          "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": 68.64039780307307,
          "uncertainty": 27.678571428571434,
          "unilateral_faults": 0,
          "wins": 42
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 74,
          "capped_draws": 69,
          "coverage_status": "rated",
          "distinct_rated_opponents": 37,
          "draws": 69,
          "evaluated_setting_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": 3,
          "model": "xiaomi/mimo-v2.5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-5f664f9580459829",
          "rated_matches": 74,
          "raw_elo_rating": 1434.8137881433222,
          "reasoning": "high",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "repaired",
          "score": 26.641010675069595,
          "uncertainty": 13.985026918962571,
          "unilateral_faults": 0,
          "wins": 2
        }
      ]
    },
    "full_freedom/mixed": {
      "GB2-01": [
        {
          "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": "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": 25,
          "model": "claude-fable-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-2dbc6efbd7db03b5",
          "rated_matches": 84,
          "raw_elo_rating": 1753.8905307528914,
          "reasoning": "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": 73.22615883803878,
          "uncertainty": 10.482614454664043,
          "unilateral_faults": 2,
          "wins": 59
        },
        {
          "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": "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": 98,
          "raw_elo_rating": 1810.7971143350485,
          "reasoning": "xhigh",
          "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": 79.68193767817715,
          "uncertainty": 6.501890762960602,
          "unilateral_faults": 0,
          "wins": 63
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 116,
          "capped_draws": 76,
          "coverage_status": "rated",
          "distinct_rated_opponents": 57,
          "draws": 76,
          "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": 25,
          "model": "claude-opus-4-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-2e3eca63f7980fac",
          "rated_matches": 116,
          "raw_elo_rating": 1460.8178118795715,
          "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": 42.428677925307234,
          "uncertainty": 2.4750163521024238,
          "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": "legacy_shared_thinking_budget",
          "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": 42,
          "capped_draws": 3,
          "coverage_status": "rated",
          "distinct_rated_opponents": 21,
          "draws": 3,
          "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": 11,
          "model": "claude-opus-4-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-5b675f86b98132f4",
          "rated_matches": 42,
          "raw_elo_rating": 1622.7522359918837,
          "reasoning": "high",
          "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": 57.24531251291242,
          "uncertainty": 32.49928516630233,
          "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": "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": "legacy_shared_thinking_budget",
          "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": 84,
          "capped_draws": 21,
          "coverage_status": "rated",
          "distinct_rated_opponents": 42,
          "draws": 21,
          "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": 21,
          "model": "claude-opus-4-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-829b603611fbdcef",
          "rated_matches": 84,
          "raw_elo_rating": 1645.6640036153567,
          "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": 61.59904938707476,
          "uncertainty": 10.482614454664043,
          "unilateral_faults": 0,
          "wins": 42
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 94,
          "capped_draws": 17,
          "coverage_status": "rated",
          "distinct_rated_opponents": 47,
          "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": 1492.718192054946,
          "reasoning": "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": 45.419750227325316,
          "uncertainty": 7.54891760425771,
          "unilateral_faults": 0,
          "wins": 38
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 102,
          "capped_draws": 14,
          "coverage_status": "rated",
          "distinct_rated_opponents": 48,
          "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-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": 102,
          "raw_elo_rating": 1604.793115128391,
          "reasoning": "xhigh",
          "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": 57.63498693048245,
          "uncertainty": 5.516463908214657,
          "unilateral_faults": 0,
          "wins": 52
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 84,
          "capped_draws": 20,
          "coverage_status": "rated",
          "distinct_rated_opponents": 42,
          "draws": 20,
          "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": 84,
          "raw_elo_rating": 1571.0311336651146,
          "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": 53.58101009021854,
          "uncertainty": 10.482614454664043,
          "unilateral_faults": 0,
          "wins": 40
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 112,
          "capped_draws": 14,
          "coverage_status": "rated",
          "distinct_rated_opponents": 56,
          "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": 37,
          "model": "claude-opus-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-0437af9582860271",
          "rated_matches": 112,
          "raw_elo_rating": 1625.1581916227758,
          "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": 60.014566638961284,
          "uncertainty": 3.286043419179858,
          "unilateral_faults": 0,
          "wins": 61
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 118,
          "capped_draws": 85,
          "coverage_status": "rated",
          "distinct_rated_opponents": 57,
          "draws": 85,
          "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": 117,
          "raw_elo_rating": 1559.7896571777924,
          "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": 53.07839841737344,
          "uncertainty": 2.2787308949161655,
          "unilateral_faults": 0,
          "wins": 18
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 68,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 30,
          "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": 68,
          "raw_elo_rating": 1844.4582749578583,
          "reasoning": "xhigh",
          "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": 82.44386303842391,
          "uncertainty": 16.4429265428846,
          "unilateral_faults": 0,
          "wins": 50
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 116,
          "capped_draws": 16,
          "coverage_status": "rated",
          "distinct_rated_opponents": 56,
          "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": 116,
          "raw_elo_rating": 1878.8405444643897,
          "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": 87.3381487667594,
          "uncertainty": 2.4750163521024238,
          "unilateral_faults": 0,
          "wins": 91
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 90,
          "capped_draws": 5,
          "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-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": 22,
          "model": "claude-opus-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-93a6875407c22137",
          "rated_matches": 90,
          "raw_elo_rating": 1808.2672310050016,
          "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": 79.22429807940591,
          "uncertainty": 8.664241836095918,
          "unilateral_faults": 0,
          "wins": 63
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 56,
          "capped_draws": 1,
          "coverage_status": "rated",
          "distinct_rated_opponents": 27,
          "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-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": 28,
          "model": "claude-opus-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-bf06fe9df8858291",
          "rated_matches": 56,
          "raw_elo_rating": 1489.1036178344127,
          "reasoning": "xhigh",
          "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": 43.74844229033586,
          "uncertainty": 22.47661785325219,
          "unilateral_faults": 0,
          "wins": 27
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 84,
          "capped_draws": 66,
          "coverage_status": "rated",
          "distinct_rated_opponents": 42,
          "draws": 66,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-sonnet-5",
            "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-12T16:00:00Z",
          "losses": 10,
          "model": "claude-sonnet-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-259fc4a9e48c81f2",
          "rated_matches": 84,
          "raw_elo_rating": 1489.6057722063917,
          "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": 44.83323249072341,
          "uncertainty": 10.482614454664043,
          "unilateral_faults": 0,
          "wins": 8
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 96,
          "capped_draws": 9,
          "coverage_status": "rated",
          "distinct_rated_opponents": 48,
          "draws": 9,
          "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-cd50a27a6bb44b58",
          "rated_matches": 96,
          "raw_elo_rating": 1561.2086367687052,
          "reasoning": "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": 52.82357979001043,
          "uncertainty": 7.017308256680951,
          "unilateral_faults": 0,
          "wins": 49
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 126,
          "capped_draws": 77,
          "coverage_status": "rated",
          "distinct_rated_opponents": 58,
          "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": 28,
          "model": "cohere/north-mini-code",
          "point_rating_method": "sequential_elo",
          "public_id": "E-194759b182ce3244",
          "rated_matches": 126,
          "raw_elo_rating": 1508.2988051809066,
          "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": 47.689326403384385,
          "uncertainty": 0.617825470805693,
          "unilateral_faults": 0,
          "wins": 21
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 96,
          "capped_draws": 21,
          "coverage_status": "rated",
          "distinct_rated_opponents": 46,
          "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": 73,
          "model": "cohere/north-mini-code",
          "point_rating_method": "sequential_elo",
          "public_id": "E-c309b463b29efb71",
          "rated_matches": 96,
          "raw_elo_rating": 1090.3276521844061,
          "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": 2.235383984912514,
          "uncertainty": 7.017308256680951,
          "unilateral_faults": 0,
          "wins": 2
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 92,
          "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": 49,
          "model": "deepseek/deepseek-v4-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-b9882650a0cde9ac",
          "rated_matches": 92,
          "raw_elo_rating": 1382.025506422629,
          "reasoning": "xhigh",
          "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": 33.4805377654376,
          "uncertainty": 8.09758473652126,
          "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": 1195.7426647399404,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "repaired",
          "score": 13.026460083495424,
          "uncertainty": 13.230288229818967,
          "unilateral_faults": 0,
          "wins": 7
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 72,
          "capped_draws": 11,
          "coverage_status": "rated",
          "distinct_rated_opponents": 36,
          "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": "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": 37,
          "model": "deepseek/deepseek-v4-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-fd9da5310ad15cac",
          "rated_matches": 72,
          "raw_elo_rating": 1569.8814747721583,
          "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": 53.08896375542971,
          "uncertainty": 14.770573598065289,
          "unilateral_faults": 0,
          "wins": 24
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 124,
          "capped_draws": 46,
          "coverage_status": "rated",
          "distinct_rated_opponents": 60,
          "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": 44,
          "model": "deepseek/deepseek-v4-pro",
          "point_rating_method": "sequential_elo",
          "public_id": "E-e121525dd1846069",
          "rated_matches": 124,
          "raw_elo_rating": 1488.5540474275292,
          "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": 45.53770120402753,
          "uncertainty": 0.9713595499957961,
          "unilateral_faults": 0,
          "wins": 34
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 96,
          "capped_draws": 19,
          "coverage_status": "rated",
          "distinct_rated_opponents": 47,
          "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": 44,
          "model": "deepseek/deepseek-v4-pro",
          "point_rating_method": "sequential_elo",
          "public_id": "E-e192048d4eaa3c43",
          "rated_matches": 96,
          "raw_elo_rating": 1475.4991443772221,
          "reasoning": "xhigh",
          "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": 43.61554479729633,
          "uncertainty": 7.017308256680951,
          "unilateral_faults": 0,
          "wins": 33
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 104,
          "capped_draws": 44,
          "coverage_status": "rated",
          "distinct_rated_opponents": 52,
          "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": 1468.2228066206737,
          "reasoning": "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": 43.00333801213897,
          "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": 1181.3686609045587,
          "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": 11.482216539302486,
          "uncertainty": 13.230288229818967,
          "unilateral_faults": 0,
          "wins": 6
        },
        {
          "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": "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": 9,
          "model": "google/gemini-3.5-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-22f31826bcf76511",
          "rated_matches": 84,
          "raw_elo_rating": 1939.5874331556233,
          "reasoning": "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": 93.17614952930187,
          "uncertainty": 10.482614454664043,
          "unilateral_faults": 0,
          "wins": 75
        },
        {
          "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": "low",
          "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": 44,
          "capped_draws": 15,
          "coverage_status": "rated",
          "distinct_rated_opponents": 22,
          "draws": 15,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "minimal",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "google/gemini-3.5-flash-lite",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 7,
          "model": "google/gemini-3.5-flash-lite",
          "point_rating_method": "sequential_elo",
          "public_id": "E-21c0edac8ac36f2e",
          "rated_matches": 44,
          "raw_elo_rating": 1578.435818592523,
          "reasoning": "minimal",
          "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": 52.63154842186275,
          "uncertainty": 30.785599249992988,
          "unilateral_faults": 0,
          "wins": 22
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 54,
          "capped_draws": 11,
          "coverage_status": "rated",
          "distinct_rated_opponents": 27,
          "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-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": 19,
          "model": "google/gemini-3.5-flash-lite",
          "point_rating_method": "sequential_elo",
          "public_id": "E-4b4f303670ce9fb6",
          "rated_matches": 54,
          "raw_elo_rating": 1526.0634598251338,
          "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": 47.6165862588399,
          "uncertainty": 23.66998624632421,
          "unilateral_faults": 0,
          "wins": 24
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 130,
          "capped_draws": 36,
          "coverage_status": "rated",
          "distinct_rated_opponents": 65,
          "draws": 36,
          "evaluated_setting_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": 42,
          "model": "google/gemini-3.5-flash-lite",
          "point_rating_method": "sequential_elo",
          "public_id": "E-77d8df8cd762fd09",
          "rated_matches": 130,
          "raw_elo_rating": 1467.128815452549,
          "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": 43.324976491572706,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 52
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 26,
          "capped_draws": 3,
          "coverage_status": "under_covered",
          "distinct_rated_opponents": 13,
          "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": "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-85d9dd9fbf531322",
          "rated_matches": 26,
          "raw_elo_rating": 1387.6764784941386,
          "reasoning": "high",
          "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": 30.273553237196605,
          "uncertainty": 52.475044864937615,
          "unilateral_faults": 0,
          "wins": 8
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 34,
          "capped_draws": 11,
          "coverage_status": "under_covered",
          "distinct_rated_opponents": 17,
          "draws": 11,
          "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": 13,
          "model": "google/gemini-3.5-flash-lite",
          "point_rating_method": "sequential_elo",
          "public_id": "E-cf51875df5447bc2",
          "rated_matches": 34,
          "raw_elo_rating": 1475.5613872584288,
          "reasoning": "minimal",
          "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": 40.72170032496317,
          "uncertainty": 40.76542547285167,
          "unilateral_faults": 0,
          "wins": 10
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 68,
          "capped_draws": 43,
          "coverage_status": "rated",
          "distinct_rated_opponents": 34,
          "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": "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-27590b9ddebe06e6",
          "rated_matches": 68,
          "raw_elo_rating": 1513.6374207779388,
          "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": 46.90275881983249,
          "uncertainty": 16.4429265428846,
          "unilateral_faults": 0,
          "wins": 16
        },
        {
          "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": "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": 96,
          "raw_elo_rating": 1982.7510820098178,
          "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": 98.1111842126933,
          "uncertainty": 7.017308256680951,
          "unilateral_faults": 0,
          "wins": 85
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 46,
          "capped_draws": 5,
          "coverage_status": "rated",
          "distinct_rated_opponents": 23,
          "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-3.6-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": 15,
          "model": "google/gemini-3.6-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-df0493ecef384a6a",
          "rated_matches": 46,
          "raw_elo_rating": 1596.815395617423,
          "reasoning": "high",
          "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": 54.743904123110745,
          "uncertainty": 29.182495748947275,
          "unilateral_faults": 0,
          "wins": 26
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 42,
          "capped_draws": 15,
          "coverage_status": "rated",
          "distinct_rated_opponents": 21,
          "draws": 15,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "minimal",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "google/gemini-3.6-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-e0c4f14c94c0a42a",
          "rated_matches": 42,
          "raw_elo_rating": 1494.6627753914672,
          "reasoning": "minimal",
          "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": 43.48426688660894,
          "uncertainty": 32.49928516630233,
          "unilateral_faults": 0,
          "wins": 15
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 46,
          "capped_draws": 12,
          "coverage_status": "rated",
          "distinct_rated_opponents": 23,
          "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": 21,
          "model": "google/gemini-3.6-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-e9260a0da3a64563",
          "rated_matches": 46,
          "raw_elo_rating": 1457.3459738996155,
          "reasoning": "high",
          "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": 39.760274191838555,
          "uncertainty": 29.182495748947275,
          "unilateral_faults": 0,
          "wins": 13
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 40,
          "capped_draws": 12,
          "coverage_status": "rated",
          "distinct_rated_opponents": 20,
          "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": "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": 15,
          "model": "google/gemini-3.6-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-e9733de94d982ade",
          "rated_matches": 40,
          "raw_elo_rating": 1426.337846925775,
          "reasoning": "minimal",
          "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": 35.985974326056116,
          "uncertainty": 34.33688094430304,
          "unilateral_faults": 0,
          "wins": 13
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 118,
          "capped_draws": 25,
          "coverage_status": "rated",
          "distinct_rated_opponents": 57,
          "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": 38,
          "model": "google/gemma-4-31b-it",
          "point_rating_method": "sequential_elo",
          "public_id": "E-caaa54d3c88e6570",
          "rated_matches": 118,
          "raw_elo_rating": 1479.4739373802697,
          "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": 44.46648998691777,
          "uncertainty": 2.084924851410568,
          "unilateral_faults": 0,
          "wins": 55
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 110,
          "capped_draws": 5,
          "coverage_status": "rated",
          "distinct_rated_opponents": 54,
          "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": 47,
          "model": "gpt-4.1",
          "point_rating_method": "sequential_elo",
          "public_id": "E-f50ec6b60d5b85da",
          "rated_matches": 109,
          "raw_elo_rating": 1591.5902539682866,
          "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": 56.353504319456164,
          "uncertainty": 3.9231294622796127,
          "unilateral_faults": 1,
          "wins": 57
        },
        {
          "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": "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": 22,
          "model": "gpt-4.1-nano",
          "point_rating_method": "sequential_elo",
          "public_id": "E-e117cfcfd3d0bf38",
          "rated_matches": 82,
          "raw_elo_rating": 1517.321654013368,
          "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": 47.75501155028078,
          "uncertainty": 11.132129994845172,
          "unilateral_faults": 0,
          "wins": 34
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 50,
          "capped_draws": 2,
          "coverage_status": "rated",
          "distinct_rated_opponents": 25,
          "draws": 2,
          "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-3e63b136f656e976",
          "rated_matches": 50,
          "raw_elo_rating": 1409.0098425181743,
          "reasoning": "high",
          "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": 34.818208622235126,
          "uncertainty": 26.264004201400486,
          "unilateral_faults": 0,
          "wins": 16
        },
        {
          "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": "low",
          "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": 92,
          "capped_draws": 17,
          "coverage_status": "rated",
          "distinct_rated_opponents": 46,
          "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": 53,
          "model": "gpt-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-adee794ecd761044",
          "rated_matches": 92,
          "raw_elo_rating": 1309.3826997250194,
          "reasoning": "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": 25.676297098775773,
          "uncertainty": 8.09758473652126,
          "unilateral_faults": 0,
          "wins": 22
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 84,
          "capped_draws": 19,
          "coverage_status": "rated",
          "distinct_rated_opponents": 41,
          "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": 82,
          "raw_elo_rating": 1700.0514577525005,
          "reasoning": "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": 67.38623768514597,
          "uncertainty": 11.132129994845172,
          "unilateral_faults": 2,
          "wins": 47
        },
        {
          "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": "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": 94,
          "raw_elo_rating": 2000.7576930253301,
          "reasoning": "xhigh",
          "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": 7.54891760425771,
          "unilateral_faults": 0,
          "wins": 89
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 98,
          "capped_draws": 2,
          "coverage_status": "rated",
          "distinct_rated_opponents": 46,
          "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": 92,
          "raw_elo_rating": 2000.7945640968424,
          "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": 99.95680517171921,
          "uncertainty": 8.09758473652126,
          "unilateral_faults": 0,
          "wins": 84
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 98,
          "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": 96,
          "raw_elo_rating": 1613.2596975548165,
          "reasoning": "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": 58.415585713195995,
          "uncertainty": 7.017308256680951,
          "unilateral_faults": 2,
          "wins": 53
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 106,
          "capped_draws": 40,
          "coverage_status": "rated",
          "distinct_rated_opponents": 52,
          "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": 44,
          "model": "gpt-5.4-mini",
          "point_rating_method": "sequential_elo",
          "public_id": "E-ea1cb793f92b3cff",
          "rated_matches": 106,
          "raw_elo_rating": 1392.215360433307,
          "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": 34.877002635313595,
          "uncertainty": 4.586824452283178,
          "unilateral_faults": 0,
          "wins": 22
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 108,
          "capped_draws": 22,
          "coverage_status": "rated",
          "distinct_rated_opponents": 54,
          "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": 1354.2534740561925,
          "reasoning": "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": 30.836930179581895,
          "uncertainty": 4.1413142610575715,
          "unilateral_faults": 0,
          "wins": 31
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 88,
          "capped_draws": 19,
          "coverage_status": "rated",
          "distinct_rated_opponents": 43,
          "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": 22,
          "model": "gpt-5.4-nano",
          "point_rating_method": "sequential_elo",
          "public_id": "E-9eb27042bf28d67c",
          "rated_matches": 88,
          "raw_elo_rating": 1626.5972093725554,
          "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": 59.65659286939674,
          "uncertainty": 9.249894000318006,
          "unilateral_faults": 0,
          "wins": 47
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 108,
          "capped_draws": 32,
          "coverage_status": "rated",
          "distinct_rated_opponents": 50,
          "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-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-a8887794a1195b75",
          "rated_matches": 102,
          "raw_elo_rating": 1578.2811745197378,
          "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": 54.78672741992332,
          "uncertainty": 5.516463908214657,
          "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": 1073.351028200554,
          "reasoning": "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": 120,
          "capped_draws": 90,
          "coverage_status": "rated",
          "distinct_rated_opponents": 59,
          "draws": 90,
          "evaluated_setting_identity": {
            "canonical_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": 120,
          "raw_elo_rating": 1515.5640194755229,
          "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": 48.376451029853435,
          "uncertainty": 1.7045454545454586,
          "unilateral_faults": 0,
          "wins": 11
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 96,
          "capped_draws": 29,
          "coverage_status": "rated",
          "distinct_rated_opponents": 44,
          "draws": 29,
          "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": 96,
          "raw_elo_rating": 1751.3774293727092,
          "reasoning": "xhigh",
          "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": 73.2539994315327,
          "uncertainty": 7.017308256680951,
          "unilateral_faults": 0,
          "wins": 51
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 104,
          "capped_draws": 61,
          "coverage_status": "rated",
          "distinct_rated_opponents": 52,
          "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-5.5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_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": 104,
          "raw_elo_rating": 1626.375137598157,
          "reasoning": "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": 59.9941304808233,
          "uncertainty": 5.045003647426665,
          "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": "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": 94,
          "raw_elo_rating": 1821.051700392042,
          "reasoning": "xhigh",
          "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": 80.69363121403609,
          "uncertainty": 7.54891760425771,
          "unilateral_faults": 0,
          "wins": 62
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 88,
          "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": 28,
          "model": "gpt-5.6-luna",
          "point_rating_method": "sequential_elo",
          "public_id": "E-4f775a5b7b265dae",
          "rated_matches": 88,
          "raw_elo_rating": 1684.1296139952278,
          "reasoning": "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": 65.83747645882278,
          "uncertainty": 9.249894000318006,
          "unilateral_faults": 0,
          "wins": 51
        },
        {
          "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": 1277.2755591791679,
          "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": 22.385721389270085,
          "uncertainty": 6.25,
          "unilateral_faults": 0,
          "wins": 14
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 92,
          "capped_draws": 11,
          "coverage_status": "rated",
          "distinct_rated_opponents": 43,
          "draws": 11,
          "evaluated_setting_identity": {
            "canonical_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": 28,
          "model": "gpt-5.6-sol",
          "point_rating_method": "sequential_elo",
          "public_id": "E-890c38b8e811c121",
          "rated_matches": 86,
          "raw_elo_rating": 1555.171019743832,
          "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": 51.9309965364074,
          "uncertainty": 9.855626741889738,
          "unilateral_faults": 0,
          "wins": 47
        },
        {
          "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": "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": 100,
          "raw_elo_rating": 1842.1038472104176,
          "reasoning": "xhigh",
          "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": 83.08829242248612,
          "uncertainty": 6.001859510499461,
          "unilateral_faults": 0,
          "wins": 77
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 98,
          "capped_draws": 1,
          "coverage_status": "rated",
          "distinct_rated_opponents": 49,
          "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": 98,
          "raw_elo_rating": 1664.1747525619378,
          "reasoning": "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": 63.92984534569066,
          "uncertainty": 6.501890762960602,
          "unilateral_faults": 0,
          "wins": 60
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 100,
          "capped_draws": 31,
          "coverage_status": "rated",
          "distinct_rated_opponents": 46,
          "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": 40,
          "model": "gpt-5.6-terra",
          "point_rating_method": "sequential_elo",
          "public_id": "E-36d36f4895d90b11",
          "rated_matches": 100,
          "raw_elo_rating": 1467.9188616540573,
          "reasoning": "xhigh",
          "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": 42.88844588724325,
          "uncertainty": 6.001859510499461,
          "unilateral_faults": 0,
          "wins": 29
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 94,
          "capped_draws": 30,
          "coverage_status": "rated",
          "distinct_rated_opponents": 46,
          "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": 35,
          "model": "gpt-5.6-terra",
          "point_rating_method": "sequential_elo",
          "public_id": "E-40742129939a44b5",
          "rated_matches": 94,
          "raw_elo_rating": 1555.7694478579945,
          "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": 52.193541012565454,
          "uncertainty": 7.54891760425771,
          "unilateral_faults": 0,
          "wins": 29
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 96,
          "capped_draws": 34,
          "coverage_status": "rated",
          "distinct_rated_opponents": 48,
          "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": 29,
          "model": "gpt-5.6-terra",
          "point_rating_method": "sequential_elo",
          "public_id": "E-46de264ad4571b48",
          "rated_matches": 96,
          "raw_elo_rating": 1507.6320452094085,
          "reasoning": "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": 47.06768139295753,
          "uncertainty": 7.017308256680951,
          "unilateral_faults": 0,
          "wins": 33
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 158,
          "capped_draws": 58,
          "coverage_status": "rated",
          "distinct_rated_opponents": 64,
          "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": 1381.054611496271,
          "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": 34.424349154668995,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 51
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 32,
          "capped_draws": 8,
          "coverage_status": "under_covered",
          "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": 1346.4764112408,
          "reasoning": "enabled",
          "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": 26.399285056998398,
          "uncertainty": 46.05265101338746,
          "unilateral_faults": 0,
          "wins": 3
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 150,
          "capped_draws": 43,
          "coverage_status": "rated",
          "distinct_rated_opponents": 58,
          "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": 65,
          "model": "inclusionai/ling-3.0-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-f9af396559c3a1cd",
          "rated_matches": 150,
          "raw_elo_rating": 1489.4165078728365,
          "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": 45.976888692310695,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 42
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 114,
          "capped_draws": 34,
          "coverage_status": "rated",
          "distinct_rated_opponents": 54,
          "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": 46,
          "model": "meituan/longcat-2.0",
          "point_rating_method": "sequential_elo",
          "public_id": "E-9f5585b5fd96f2c3",
          "rated_matches": 114,
          "raw_elo_rating": 1434.1444270156533,
          "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": 39.52867611705157,
          "uncertainty": 2.875240412015687,
          "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": 1380.9335045784128,
          "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": 34.006079518097124,
          "uncertainty": 0.617825470805693,
          "unilateral_faults": 0,
          "wins": 31
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 122,
          "capped_draws": 24,
          "coverage_status": "rated",
          "distinct_rated_opponents": 60,
          "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": 38,
          "model": "minimax/minimax-m3",
          "point_rating_method": "sequential_elo",
          "public_id": "E-444510032bc433fc",
          "rated_matches": 122,
          "raw_elo_rating": 1543.4553724122525,
          "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": 51.404796674852406,
          "uncertainty": 1.3334817333716131,
          "unilateral_faults": 0,
          "wins": 60
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 60,
          "capped_draws": 4,
          "coverage_status": "rated",
          "distinct_rated_opponents": 30,
          "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": "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": 45,
          "model": "minimax/minimax-m3",
          "point_rating_method": "sequential_elo",
          "public_id": "E-e0a841a9daa66219",
          "rated_matches": 60,
          "raw_elo_rating": 1270.7648026910003,
          "reasoning": "enabled",
          "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": 20.481415371098425,
          "uncertainty": 20.268439966447993,
          "unilateral_faults": 0,
          "wins": 11
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 44,
          "capped_draws": 2,
          "coverage_status": "rated",
          "distinct_rated_opponents": 22,
          "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": "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": 41,
          "model": "mistralai/mistral-medium-3-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-99c7b0d758665b66",
          "rated_matches": 44,
          "raw_elo_rating": 1185.7659955378595,
          "reasoning": "high",
          "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": 10.445818809147307,
          "uncertainty": 30.785599249992988,
          "unilateral_faults": 0,
          "wins": 1
        },
        {
          "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": 1483.4317022040432,
          "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": 44.576050565533166,
          "uncertainty": 5.757377148833722,
          "unilateral_faults": 35,
          "wins": 43
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 62,
          "capped_draws": 2,
          "coverage_status": "rated",
          "distinct_rated_opponents": 31,
          "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": "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": 34,
          "model": "moonshotai/kimi-k2.7-code",
          "point_rating_method": "sequential_elo",
          "public_id": "E-4935e918b1e70ea1",
          "rated_matches": 62,
          "raw_elo_rating": 1480.7658314862003,
          "reasoning": "enabled",
          "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": 43.13051350484086,
          "uncertainty": 19.244078834871203,
          "unilateral_faults": 0,
          "wins": 26
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 34,
          "capped_draws": 4,
          "coverage_status": "under_covered",
          "distinct_rated_opponents": 13,
          "draws": 4,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "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-58aadd759ee9fa72",
          "rated_matches": 26,
          "raw_elo_rating": 1550.9709158159071,
          "reasoning": "high",
          "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": 47.816778042525385,
          "uncertainty": 52.475044864937615,
          "unilateral_faults": 0,
          "wins": 12
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 44,
          "capped_draws": 2,
          "coverage_status": "rated",
          "distinct_rated_opponents": 22,
          "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": "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": 22,
          "model": "moonshotai/kimi-k3",
          "point_rating_method": "sequential_elo",
          "public_id": "E-dbb89dcf5242a5a0",
          "rated_matches": 44,
          "raw_elo_rating": 1513.6885084246553,
          "reasoning": "max",
          "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": 45.67554528761618,
          "uncertainty": 30.785599249992988,
          "unilateral_faults": 0,
          "wins": 20
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 66,
          "capped_draws": 47,
          "coverage_status": "rated",
          "distinct_rated_opponents": 33,
          "draws": 47,
          "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": 7,
          "model": "moonshotai/kimi-k3",
          "point_rating_method": "sequential_elo",
          "public_id": "E-fb8801908d28001f",
          "rated_matches": 66,
          "raw_elo_rating": 1543.8316411636547,
          "reasoning": "low",
          "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": 50.06997031510964,
          "uncertainty": 17.33472217815261,
          "unilateral_faults": 0,
          "wins": 12
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 82,
          "capped_draws": 14,
          "coverage_status": "rated",
          "distinct_rated_opponents": 41,
          "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": 40,
          "model": "nvidia/nemotron-3-ultra-550b-a55b",
          "point_rating_method": "sequential_elo",
          "public_id": "E-0ce5e196701b51f3",
          "rated_matches": 82,
          "raw_elo_rating": 1574.046272202658,
          "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": 53.84911215292571,
          "uncertainty": 11.132129994845172,
          "unilateral_faults": 0,
          "wins": 28
        },
        {
          "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": "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": 94,
          "raw_elo_rating": 1525.958621253768,
          "reasoning": "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": 48.990872009700986,
          "uncertainty": 7.54891760425771,
          "unilateral_faults": 0,
          "wins": 38
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 44,
          "capped_draws": 3,
          "coverage_status": "rated",
          "distinct_rated_opponents": 22,
          "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": "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": 37,
          "model": "nvidia/nemotron-3-ultra-550b-a55b",
          "point_rating_method": "sequential_elo",
          "public_id": "E-ce064a9927030b28",
          "rated_matches": 44,
          "raw_elo_rating": 1255.6725026396348,
          "reasoning": "high",
          "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": 17.9560903747683,
          "uncertainty": 30.785599249992988,
          "unilateral_faults": 0,
          "wins": 4
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 48,
          "capped_draws": 1,
          "coverage_status": "rated",
          "distinct_rated_opponents": 24,
          "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-03T15:45:00Z",
          "losses": 20,
          "model": "o3",
          "point_rating_method": "sequential_elo",
          "public_id": "E-01ad69b67b42a9e7",
          "rated_matches": 48,
          "raw_elo_rating": 1570.1252117794763,
          "reasoning": "high",
          "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": 52.005752373767585,
          "uncertainty": 27.678571428571434,
          "unilateral_faults": 0,
          "wins": 27
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 48,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 24,
          "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-03T16:00:00Z",
          "losses": 18,
          "model": "o3",
          "point_rating_method": "sequential_elo",
          "public_id": "E-21b0558e9f2190f7",
          "rated_matches": 48,
          "raw_elo_rating": 1622.4157835264396,
          "reasoning": "high",
          "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": 57.623489697841514,
          "uncertainty": 27.678571428571434,
          "unilateral_faults": 0,
          "wins": 30
        },
        {
          "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": 1494.2465984289327,
          "reasoning": "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": 45.6739398929183,
          "uncertainty": 6.501890762960602,
          "unilateral_faults": 0,
          "wins": 35
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 26,
          "capped_draws": 5,
          "coverage_status": "under_covered",
          "distinct_rated_opponents": 13,
          "draws": 5,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "o3",
            "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-03T15:50:00Z",
          "losses": 14,
          "model": "o3",
          "point_rating_method": "sequential_elo",
          "public_id": "E-5e8b87fcfa2225fd",
          "rated_matches": 26,
          "raw_elo_rating": 1451.401909856562,
          "reasoning": "high",
          "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": 37.11977278112783,
          "uncertainty": 52.475044864937615,
          "unilateral_faults": 0,
          "wins": 7
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 50,
          "capped_draws": 18,
          "coverage_status": "rated",
          "distinct_rated_opponents": 25,
          "draws": 18,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "low",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "o3",
            "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-21T14:20:15Z",
          "losses": 27,
          "model": "o3",
          "point_rating_method": "sequential_elo",
          "public_id": "E-cb2bd51b4adfa607",
          "rated_matches": 50,
          "raw_elo_rating": 1346.0195035899546,
          "reasoning": "low",
          "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": 28.05096232465229,
          "uncertainty": 26.264004201400486,
          "unilateral_faults": 0,
          "wins": 5
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 58,
          "capped_draws": 14,
          "coverage_status": "rated",
          "distinct_rated_opponents": 29,
          "draws": 14,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "low",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "openai/gpt-oss-120b",
            "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-21T14:20:15Z",
          "losses": 32,
          "model": "openai/gpt-oss-120b",
          "point_rating_method": "sequential_elo",
          "public_id": "E-55f6c0e3dc8a8065",
          "rated_matches": 58,
          "raw_elo_rating": 1353.7738933916733,
          "reasoning": "low",
          "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": 29.30685815347161,
          "uncertainty": 21.344455490411935,
          "unilateral_faults": 0,
          "wins": 12
        },
        {
          "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": 1456.6726793206537,
          "reasoning": "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": 41.54726967322666,
          "uncertainty": 7.54891760425771,
          "unilateral_faults": 0,
          "wins": 27
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 118,
          "capped_draws": 20,
          "coverage_status": "rated",
          "distinct_rated_opponents": 58,
          "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": 57,
          "model": "poolside/laguna-s-2.1",
          "point_rating_method": "sequential_elo",
          "public_id": "E-8461eb1b16e40129",
          "rated_matches": 118,
          "raw_elo_rating": 1588.875259183409,
          "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": 56.21981125046297,
          "uncertainty": 2.084924851410568,
          "unilateral_faults": 0,
          "wins": 41
        },
        {
          "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": "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": 45,
          "model": "poolside/laguna-s-2.1",
          "point_rating_method": "sequential_elo",
          "public_id": "E-c58ec61528547516",
          "rated_matches": 116,
          "raw_elo_rating": 1458.5679351295464,
          "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": 42.186966730135296,
          "uncertainty": 2.4750163521024238,
          "unilateral_faults": 0,
          "wins": 37
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 20,
          "capped_draws": 2,
          "coverage_status": "under_covered",
          "distinct_rated_opponents": 10,
          "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": "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": 8,
          "model": "poolside/laguna-s-2.1",
          "point_rating_method": "sequential_elo",
          "public_id": "E-ffd72d2c5c11728a",
          "rated_matches": 20,
          "raw_elo_rating": 1478.3465273519382,
          "reasoning": "enabled",
          "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": 38.90719040535941,
          "uncertainty": 65.3589451179962,
          "unilateral_faults": 0,
          "wins": 10
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 58,
          "capped_draws": 11,
          "coverage_status": "rated",
          "distinct_rated_opponents": 29,
          "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": "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": 40,
          "model": "qwen/qwen3.7-max",
          "point_rating_method": "sequential_elo",
          "public_id": "E-24581eb49b81bf8f",
          "rated_matches": 58,
          "raw_elo_rating": 1316.8370332315765,
          "reasoning": "enabled",
          "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": 25.33861739757424,
          "uncertainty": 21.344455490411935,
          "unilateral_faults": 0,
          "wins": 7
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 102,
          "capped_draws": 23,
          "coverage_status": "rated",
          "distinct_rated_opponents": 48,
          "draws": 23,
          "evaluated_setting_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": 96,
          "raw_elo_rating": 1572.4078988417914,
          "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": 54.02675103959072,
          "uncertainty": 7.017308256680951,
          "unilateral_faults": 0,
          "wins": 43
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 56,
          "capped_draws": 7,
          "coverage_status": "rated",
          "distinct_rated_opponents": 28,
          "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": "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": 21,
          "model": "qwen/qwen3.7-plus",
          "point_rating_method": "sequential_elo",
          "public_id": "E-1e5dceaf2ba3ca9a",
          "rated_matches": 56,
          "raw_elo_rating": 1548.1271187402674,
          "reasoning": "enabled",
          "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": 50.0895189502136,
          "uncertainty": 22.47661785325219,
          "unilateral_faults": 0,
          "wins": 28
        },
        {
          "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": 1351.2113457571206,
          "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": 30.350197668676998,
          "uncertainty": 6.001859510499461,
          "unilateral_faults": 0,
          "wins": 19
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 42,
          "capped_draws": 1,
          "coverage_status": "rated",
          "distinct_rated_opponents": 21,
          "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": "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": 39,
          "model": "stepfun/step-3.7-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-4b0ce2bc67b08d8a",
          "rated_matches": 42,
          "raw_elo_rating": 1196.3552850945189,
          "reasoning": "high",
          "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": 11.436173582115469,
          "uncertainty": 32.49928516630233,
          "unilateral_faults": 0,
          "wins": 2
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 46,
          "capped_draws": 4,
          "coverage_status": "rated",
          "distinct_rated_opponents": 23,
          "draws": 4,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "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": 16,
          "model": "tencent/hy3-preview",
          "point_rating_method": "sequential_elo",
          "public_id": "E-29e8870e43d717e5",
          "rated_matches": 46,
          "raw_elo_rating": 1572.2892822260337,
          "reasoning": "high",
          "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": 52.1089881524075,
          "uncertainty": 29.182495748947275,
          "unilateral_faults": 0,
          "wins": 26
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 102,
          "capped_draws": 17,
          "coverage_status": "rated",
          "distinct_rated_opponents": 48,
          "draws": 17,
          "evaluated_setting_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": 96,
          "raw_elo_rating": 1734.2538039468136,
          "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": 71.41435556334146,
          "uncertainty": 7.017308256680951,
          "unilateral_faults": 0,
          "wins": 60
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 54,
          "capped_draws": 13,
          "coverage_status": "rated",
          "distinct_rated_opponents": 27,
          "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",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "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": "thinkingmachines/inkling",
          "point_rating_method": "sequential_elo",
          "public_id": "E-46c7f693daaae605",
          "rated_matches": 54,
          "raw_elo_rating": 1407.8495385633466,
          "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": 34.916500267983515,
          "uncertainty": 23.66998624632421,
          "unilateral_faults": 0,
          "wins": 14
        },
        {
          "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": 1281.5213970678337,
          "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": 23.16631134735838,
          "uncertainty": 2.4750163521024238,
          "unilateral_faults": 0,
          "wins": 16
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 28,
          "capped_draws": 15,
          "coverage_status": "under_covered",
          "distinct_rated_opponents": 14,
          "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",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "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-ab1de1dc51400446",
          "rated_matches": 28,
          "raw_elo_rating": 1354.9663293370681,
          "reasoning": "max",
          "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": 27.049674587596016,
          "uncertainty": 49.09766908852594,
          "unilateral_faults": 0,
          "wins": 2
        },
        {
          "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": 1146.1984499521122,
          "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": 8.5937521216808,
          "uncertainty": 2.875240412015687,
          "unilateral_faults": 0,
          "wins": 6
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 36,
          "capped_draws": 6,
          "coverage_status": "under_covered",
          "distinct_rated_opponents": 18,
          "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": "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": 6,
          "model": "x-ai/grok-4.5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-1c8e452ede41ea2e",
          "rated_matches": 36,
          "raw_elo_rating": 1677.8705995787811,
          "reasoning": "high",
          "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": 62.6554488390747,
          "uncertainty": 38.449493652678655,
          "unilateral_faults": 0,
          "wins": 24
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 68,
          "capped_draws": 44,
          "coverage_status": "rated",
          "distinct_rated_opponents": 34,
          "draws": 44,
          "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": 6,
          "model": "x-ai/grok-4.5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-7ee1b68d1249ac22",
          "rated_matches": 68,
          "raw_elo_rating": 1580.8420803513893,
          "reasoning": "low",
          "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": 54.12276257623396,
          "uncertainty": 16.4429265428846,
          "unilateral_faults": 0,
          "wins": 18
        },
        {
          "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": 1799.055667309865,
          "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": 78.50521178364832,
          "uncertainty": 5.516463908214657,
          "unilateral_faults": 2,
          "wins": 73
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 62,
          "capped_draws": 10,
          "coverage_status": "rated",
          "distinct_rated_opponents": 31,
          "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": "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": 30,
          "model": "x-ai/grok-build-0.1",
          "point_rating_method": "sequential_elo",
          "public_id": "E-f1ded648f3ab17dc",
          "rated_matches": 62,
          "raw_elo_rating": 1482.4848219509731,
          "reasoning": "enabled",
          "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": 43.3151899497727,
          "uncertainty": 19.244078834871203,
          "unilateral_faults": 0,
          "wins": 22
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 62,
          "capped_draws": 3,
          "coverage_status": "rated",
          "distinct_rated_opponents": 31,
          "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": 34,
          "model": "xiaomi/mimo-v2.5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-1208f50b0908ecb4",
          "rated_matches": 62,
          "raw_elo_rating": 1399.8536397077935,
          "reasoning": "enabled",
          "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": 34.43786730610081,
          "uncertainty": 19.244078834871203,
          "unilateral_faults": 0,
          "wins": 25
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 50,
          "capped_draws": 3,
          "coverage_status": "rated",
          "distinct_rated_opponents": 25,
          "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": "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": 34,
          "model": "xiaomi/mimo-v2.5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-2a71bee21bd7c0b9",
          "rated_matches": 50,
          "raw_elo_rating": 1401.127265205498,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "repaired",
          "score": 33.97135904113655,
          "uncertainty": 26.264004201400486,
          "unilateral_faults": 0,
          "wins": 13
        },
        {
          "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": "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": 90,
          "raw_elo_rating": 1576.888139347102,
          "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": 54.36652896747432,
          "uncertainty": 8.664241836095918,
          "unilateral_faults": 0,
          "wins": 44
        },
        {
          "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": 1251.9402308692768,
          "reasoning": "high",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "repaired",
          "score": 18.9315557741441,
          "uncertainty": 14.770573598065289,
          "unilateral_faults": 0,
          "wins": 2
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 118,
          "capped_draws": 27,
          "coverage_status": "rated",
          "distinct_rated_opponents": 58,
          "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": 49,
          "model": "xiaomi/mimo-v2.5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-912a4a40bbdcbd45",
          "rated_matches": 118,
          "raw_elo_rating": 1521.4048391771312,
          "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": 48.97125603147698,
          "uncertainty": 2.084924851410568,
          "unilateral_faults": 0,
          "wins": 42
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 98,
          "capped_draws": 29,
          "coverage_status": "rated",
          "distinct_rated_opponents": 49,
          "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": 41,
          "model": "xiaomi/mimo-v2.5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-a168350bd057f924",
          "rated_matches": 98,
          "raw_elo_rating": 1437.9016164420188,
          "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": 39.620624777836554,
          "uncertainty": 6.501890762960602,
          "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": 1427.5356647847705,
          "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": 38.853074260758646,
          "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": 1481.5688155862535,
          "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": 43.91397389925815,
          "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": 1243.092112701758,
          "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": 18.048490123576414,
          "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": 1469.1718670852033,
          "reasoning": "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": 42.524252957277774,
          "uncertainty": 11.805555555555554,
          "unilateral_faults": 0,
          "wins": 43
        }
      ],
      "GB2-02": [
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 78,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 38,
          "draws": 30,
          "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": 76,
          "raw_elo_rating": 1690.47443747152,
          "reasoning": "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": 72.88223492302193,
          "uncertainty": 13.230288229818967,
          "unilateral_faults": 2,
          "wins": 37
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 82,
          "capped_draws": 0,
          "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-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": 82,
          "raw_elo_rating": 1701.6468619133602,
          "reasoning": "xhigh",
          "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": 75.80812316419362,
          "uncertainty": 11.132129994845172,
          "unilateral_faults": 0,
          "wins": 41
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 60,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 30,
          "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-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": 4,
          "model": "claude-opus-4-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-03472a04778e9928",
          "rated_matches": 60,
          "raw_elo_rating": 1499.262611968492,
          "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": 28.065418891234213,
          "uncertainty": 20.268439966447993,
          "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": "legacy_shared_thinking_budget",
          "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": 90,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 45,
          "draws": 74,
          "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": 90,
          "raw_elo_rating": 1493.9783604804352,
          "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": 28.975930507597035,
          "uncertainty": 8.664241836095918,
          "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": "legacy_shared_thinking_budget",
          "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": 30,
          "capped_draws": 0,
          "coverage_status": "under_covered",
          "distinct_rated_opponents": 15,
          "draws": 23,
          "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": 7,
          "model": "claude-opus-4-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-63fde27ceab11930",
          "rated_matches": 30,
          "raw_elo_rating": 1434.0593552461078,
          "reasoning": "high",
          "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": 8.52361085885523,
          "uncertainty": 46.05265101338746,
          "unilateral_faults": 0,
          "wins": 0
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 82,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 35,
          "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": 82,
          "raw_elo_rating": 1729.077401945733,
          "reasoning": "xhigh",
          "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": 82.05347374902418,
          "uncertainty": 11.132129994845172,
          "unilateral_faults": 0,
          "wins": 45
        },
        {
          "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": 1470.3374865351009,
          "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": 22.761732969686722,
          "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": 1459.9363913520322,
          "reasoning": "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": 20.525841154304743,
          "uncertainty": 12.5043950463012,
          "unilateral_faults": 0,
          "wins": 1
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 72,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 36,
          "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-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-50b401cafe71e710",
          "rated_matches": 72,
          "raw_elo_rating": 1653.2897177516088,
          "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": 64.13551289470387,
          "uncertainty": 14.770573598065289,
          "unilateral_faults": 0,
          "wins": 33
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 90,
          "capped_draws": 0,
          "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": "2026-07-25T10:50:00Z",
          "losses": 10,
          "model": "claude-opus-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-51ddad48e10b006f",
          "rated_matches": 90,
          "raw_elo_rating": 1671.2479236604809,
          "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": 69.336439953367,
          "uncertainty": 8.664241836095918,
          "unilateral_faults": 0,
          "wins": 56
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 56,
          "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": 56,
          "raw_elo_rating": 1636.8705409386753,
          "reasoning": "xhigh",
          "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": 58.99361361961407,
          "uncertainty": 22.47661785325219,
          "unilateral_faults": 0,
          "wins": 21
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 88,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 44,
          "draws": 46,
          "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": 88,
          "raw_elo_rating": 1643.7537400063634,
          "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": 62.96992663548684,
          "uncertainty": 9.249894000318006,
          "unilateral_faults": 0,
          "wins": 38
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 72,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 36,
          "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-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": 72,
          "raw_elo_rating": 1649.7760660413985,
          "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": 63.33552912707279,
          "uncertainty": 14.770573598065289,
          "unilateral_faults": 0,
          "wins": 32
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 58,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 23,
          "draws": 12,
          "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": 58,
          "raw_elo_rating": 1750.208365973637,
          "reasoning": "xhigh",
          "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": 85.00444139491074,
          "uncertainty": 21.344455490411935,
          "unilateral_faults": 0,
          "wins": 35
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 76,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 38,
          "draws": 71,
          "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": 76,
          "raw_elo_rating": 1487.86953058894,
          "reasoning": "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": 26.753406537020762,
          "uncertainty": 13.230288229818967,
          "unilateral_faults": 0,
          "wins": 1
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 64,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 32,
          "draws": 54,
          "evaluated_setting_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": 10,
          "model": "deepseek/deepseek-v4-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-08e2baea96c43eb4",
          "rated_matches": 64,
          "raw_elo_rating": 1444.9368175852394,
          "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": 16.06107223859427,
          "uncertainty": 18.26736729460423,
          "unilateral_faults": 0,
          "wins": 0
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 70,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 35,
          "draws": 57,
          "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": 9,
          "model": "deepseek/deepseek-v4-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-12dcb25370550495",
          "rated_matches": 70,
          "raw_elo_rating": 1496.9276220539098,
          "reasoning": "xhigh",
          "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": 28.386103413880857,
          "uncertainty": 15.58908290969266,
          "unilateral_faults": 0,
          "wins": 4
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 68,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 34,
          "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": "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": 68,
          "raw_elo_rating": 1488.5381352612483,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "repaired",
          "score": 26.320474066181795,
          "uncertainty": 16.4429265428846,
          "unilateral_faults": 0,
          "wins": 2
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 82,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 41,
          "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": "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": 82,
          "raw_elo_rating": 1471.1514124728146,
          "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": 23.329211401413826,
          "uncertainty": 11.132129994845172,
          "unilateral_faults": 0,
          "wins": 1
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 86,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 43,
          "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": "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": 86,
          "raw_elo_rating": 1479.248896520903,
          "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": 25.40534241954475,
          "uncertainty": 9.855626741889738,
          "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": 1482.8419989760441,
          "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": 24.513374734358962,
          "uncertainty": 19.244078834871203,
          "unilateral_faults": 0,
          "wins": 1
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 90,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 45,
          "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",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_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": 90,
          "raw_elo_rating": 1495.3389302620424,
          "reasoning": "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": 29.285703310875242,
          "uncertainty": 8.664241836095918,
          "unilateral_faults": 0,
          "wins": 10
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 26,
          "capped_draws": 0,
          "coverage_status": "under_covered",
          "distinct_rated_opponents": 13,
          "draws": 22,
          "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": 3,
          "model": "google/gemini-3.5-flash-lite",
          "point_rating_method": "sequential_elo",
          "public_id": "E-1010911d64a09b68",
          "rated_matches": 26,
          "raw_elo_rating": 1479.4002573381329,
          "reasoning": "minimal",
          "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": 17.676975981941407,
          "uncertainty": 52.475044864937615,
          "unilateral_faults": 0,
          "wins": 1
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 20,
          "capped_draws": 0,
          "coverage_status": "under_covered",
          "distinct_rated_opponents": 10,
          "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": "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": 3,
          "model": "google/gemini-3.5-flash-lite",
          "point_rating_method": "sequential_elo",
          "public_id": "E-423f6c31467b8943",
          "rated_matches": 20,
          "raw_elo_rating": 1469.3649644456032,
          "reasoning": "high",
          "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": 13.045441153620832,
          "uncertainty": 65.3589451179962,
          "unilateral_faults": 0,
          "wins": 1
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 36,
          "capped_draws": 0,
          "coverage_status": "under_covered",
          "distinct_rated_opponents": 18,
          "draws": 36,
          "evaluated_setting_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": 0,
          "model": "google/gemini-3.5-flash-lite",
          "point_rating_method": "sequential_elo",
          "public_id": "E-dbbc5835674b5f2c",
          "rated_matches": 36,
          "raw_elo_rating": 1494.8163977249776,
          "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": 23.741559061870756,
          "uncertainty": 38.449493652678655,
          "unilateral_faults": 0,
          "wins": 0
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 30,
          "capped_draws": 0,
          "coverage_status": "under_covered",
          "distinct_rated_opponents": 15,
          "draws": 29,
          "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": 1,
          "model": "google/gemini-3.5-flash-lite",
          "point_rating_method": "sequential_elo",
          "public_id": "E-e65fdcb71f09a611",
          "rated_matches": 30,
          "raw_elo_rating": 1479.348920615594,
          "reasoning": "minimal",
          "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": 18.835081695128604,
          "uncertainty": 46.05265101338746,
          "unilateral_faults": 0,
          "wins": 0
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 28,
          "capped_draws": 0,
          "coverage_status": "under_covered",
          "distinct_rated_opponents": 14,
          "draws": 27,
          "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": 1,
          "model": "google/gemini-3.6-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-4492f6d65cd6280b",
          "rated_matches": 28,
          "raw_elo_rating": 1482.3135878183718,
          "reasoning": "minimal",
          "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": 18.95544468148222,
          "uncertainty": 49.09766908852594,
          "unilateral_faults": 0,
          "wins": 0
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 86,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 43,
          "draws": 80,
          "evaluated_setting_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": 86,
          "raw_elo_rating": 1464.156172217111,
          "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": 21.969050080927598,
          "uncertainty": 9.855626741889738,
          "unilateral_faults": 0,
          "wins": 1
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 28,
          "capped_draws": 0,
          "coverage_status": "under_covered",
          "distinct_rated_opponents": 14,
          "draws": 27,
          "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": 1,
          "model": "google/gemini-3.6-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-9c8b43dc41bad760",
          "rated_matches": 28,
          "raw_elo_rating": 1484.8758512553966,
          "reasoning": "minimal",
          "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": 19.538817573012135,
          "uncertainty": 49.09766908852594,
          "unilateral_faults": 0,
          "wins": 0
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 84,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 42,
          "draws": 70,
          "evaluated_setting_identity": {
            "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": 84,
          "raw_elo_rating": 1463.4359726589596,
          "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": 21.690874544258786,
          "uncertainty": 10.482614454664043,
          "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": "low",
          "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": 32,
          "capped_draws": 0,
          "coverage_status": "under_covered",
          "distinct_rated_opponents": 16,
          "draws": 22,
          "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": 8,
          "model": "gpt-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-5bccb9b671ce5eae",
          "rated_matches": 32,
          "raw_elo_rating": 1451.374404650968,
          "reasoning": "high",
          "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": 12.969290339907706,
          "uncertainty": 43.288827977848925,
          "unilateral_faults": 0,
          "wins": 2
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 80,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 35,
          "draws": 49,
          "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": 80,
          "raw_elo_rating": 1620.5373124406053,
          "reasoning": "xhigh",
          "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": 57.21854400867016,
          "uncertainty": 11.805555555555554,
          "unilateral_faults": 0,
          "wins": 22
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 84,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 41,
          "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",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_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": 84,
          "raw_elo_rating": 1467.3031221858107,
          "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": 22.571342246704436,
          "uncertainty": 10.482614454664043,
          "unilateral_faults": 0,
          "wins": 1
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 80,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 40,
          "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": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_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": 80,
          "raw_elo_rating": 1471.4974252789027,
          "reasoning": "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": 23.285331416066995,
          "uncertainty": 11.805555555555554,
          "unilateral_faults": 0,
          "wins": 4
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 84,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 41,
          "draws": 82,
          "evaluated_setting_identity": {
            "canonical_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": 84,
          "raw_elo_rating": 1469.565751019137,
          "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": 23.086494711467868,
          "uncertainty": 10.482614454664043,
          "unilateral_faults": 0,
          "wins": 0
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 90,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 45,
          "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": 1478.9493057309376,
          "reasoning": "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": 25.554134372396923,
          "uncertainty": 8.664241836095918,
          "unilateral_faults": 0,
          "wins": 3
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 86,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 43,
          "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-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": 86,
          "raw_elo_rating": 1467.2273330893977,
          "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": 22.668288095462078,
          "uncertainty": 9.855626741889738,
          "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": 1475.5653849402343,
          "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": 24.56668517191457,
          "uncertainty": 9.855626741889738,
          "unilateral_faults": 0,
          "wins": 4
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 78,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 39,
          "draws": 75,
          "evaluated_setting_identity": {
            "canonical_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": 78,
          "raw_elo_rating": 1482.129902029356,
          "reasoning": "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": 25.578831533804646,
          "uncertainty": 12.5043950463012,
          "unilateral_faults": 0,
          "wins": 0
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 82,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 41,
          "draws": 73,
          "evaluated_setting_identity": {
            "canonical_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": 82,
          "raw_elo_rating": 1477.8084557546495,
          "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": 24.844878577648164,
          "uncertainty": 11.132129994845172,
          "unilateral_faults": 0,
          "wins": 0
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 72,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 36,
          "draws": 43,
          "evaluated_setting_identity": {
            "canonical_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": 72,
          "raw_elo_rating": 1580.4346988559294,
          "reasoning": "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": 47.54797454033727,
          "uncertainty": 14.770573598065289,
          "unilateral_faults": 0,
          "wins": 20
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 84,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 42,
          "draws": 71,
          "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": 84,
          "raw_elo_rating": 1469.0532689115892,
          "reasoning": "xhigh",
          "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": 22.96981343482104,
          "uncertainty": 10.482614454664043,
          "unilateral_faults": 0,
          "wins": 3
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 84,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 42,
          "draws": 82,
          "evaluated_setting_identity": {
            "canonical_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": 84,
          "raw_elo_rating": 1475.3176618766922,
          "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": 24.39608248464808,
          "uncertainty": 10.482614454664043,
          "unilateral_faults": 0,
          "wins": 0
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 70,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 35,
          "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-5.6-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": 70,
          "raw_elo_rating": 1473.5711246807089,
          "reasoning": "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": 23.068325697614167,
          "uncertainty": 15.58908290969266,
          "unilateral_faults": 0,
          "wins": 0
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 70,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 35,
          "draws": 56,
          "evaluated_setting_identity": {
            "canonical_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": 70,
          "raw_elo_rating": 1495.2258908916226,
          "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": 27.998655419890518,
          "uncertainty": 15.58908290969266,
          "unilateral_faults": 0,
          "wins": 5
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 76,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 38,
          "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-5.6-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-087d760c91df7f17",
          "rated_matches": 76,
          "raw_elo_rating": 1582.2391207094831,
          "reasoning": "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": 48.239355196944736,
          "uncertainty": 13.230288229818967,
          "unilateral_faults": 0,
          "wins": 27
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 86,
          "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": 86,
          "raw_elo_rating": 1806.880102034298,
          "reasoning": "xhigh",
          "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": 9.855626741889738,
          "unilateral_faults": 0,
          "wins": 60
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 86,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 37,
          "draws": 50,
          "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": 86,
          "raw_elo_rating": 1580.2699961396245,
          "reasoning": "xhigh",
          "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": 48.40569833085461,
          "uncertainty": 9.855626741889738,
          "unilateral_faults": 0,
          "wins": 16
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 84,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 42,
          "draws": 75,
          "evaluated_setting_identity": {
            "canonical_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": 84,
          "raw_elo_rating": 1484.6607459565766,
          "reasoning": "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": 26.523304025075756,
          "uncertainty": 10.482614454664043,
          "unilateral_faults": 0,
          "wins": 0
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 100,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 50,
          "draws": 87,
          "evaluated_setting_identity": {
            "canonical_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": 100,
          "raw_elo_rating": 1502.7441141687189,
          "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": 31.456640462802426,
          "uncertainty": 6.001859510499461,
          "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": 1444.502691239462,
          "reasoning": "enabled",
          "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": 8.268540367052571,
          "uncertainty": 60.5072070285374,
          "unilateral_faults": 0,
          "wins": 0
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 118,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 51,
          "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": 1459.7462631719882,
          "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": 22.380386424640683,
          "uncertainty": 2.084924851410568,
          "unilateral_faults": 0,
          "wins": 1
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 16,
          "capped_draws": 0,
          "coverage_status": "under_covered",
          "distinct_rated_opponents": 8,
          "draws": 16,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "enabled",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "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": 0,
          "model": "meituan/longcat-2.0",
          "point_rating_method": "sequential_elo",
          "public_id": "E-a00d8e3eb7dd07cf",
          "rated_matches": 16,
          "raw_elo_rating": 1493.6506550614847,
          "reasoning": "enabled",
          "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": 16.36012399547446,
          "uncertainty": 77.5178125181665,
          "unilateral_faults": 0,
          "wins": 0
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 98,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 49,
          "draws": 93,
          "evaluated_setting_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": 98,
          "raw_elo_rating": 1471.8760079780336,
          "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": 24.33755198695994,
          "uncertainty": 6.501890762960602,
          "unilateral_faults": 0,
          "wins": 0
        },
        {
          "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": 1462.4496711139095,
          "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": 20.685292976640326,
          "uncertainty": 14.770573598065289,
          "unilateral_faults": 0,
          "wins": 0
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 48,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 24,
          "draws": 37,
          "evaluated_setting_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": 11,
          "model": "minimax/minimax-m3",
          "point_rating_method": "sequential_elo",
          "public_id": "E-cad87bcb23d33fef",
          "rated_matches": 48,
          "raw_elo_rating": 1423.4954691324942,
          "reasoning": "enabled",
          "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": 9.465148378582635,
          "uncertainty": 27.678571428571434,
          "unilateral_faults": 0,
          "wins": 0
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 58,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 29,
          "draws": 49,
          "evaluated_setting_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": 7,
          "model": "moonshotai/kimi-k2.7-code",
          "point_rating_method": "sequential_elo",
          "public_id": "E-85c8a9372a607001",
          "rated_matches": 58,
          "raw_elo_rating": 1474.266865658278,
          "reasoning": "enabled",
          "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": 22.17843037435877,
          "uncertainty": 21.344455490411935,
          "unilateral_faults": 0,
          "wins": 2
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 24,
          "capped_draws": 0,
          "coverage_status": "under_covered",
          "distinct_rated_opponents": 12,
          "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": 4,
          "model": "moonshotai/kimi-k3",
          "point_rating_method": "sequential_elo",
          "public_id": "E-0c4144684fc36307",
          "rated_matches": 24,
          "raw_elo_rating": 1529.971155279276,
          "reasoning": "high",
          "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": 28.503312323598145,
          "uncertainty": 56.25,
          "unilateral_faults": 0,
          "wins": 4
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 32,
          "capped_draws": 0,
          "coverage_status": "under_covered",
          "distinct_rated_opponents": 16,
          "draws": 22,
          "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": 8,
          "model": "moonshotai/kimi-k3",
          "point_rating_method": "sequential_elo",
          "public_id": "E-1beeecccf3f2c84f",
          "rated_matches": 32,
          "raw_elo_rating": 1475.6155697362992,
          "reasoning": "max",
          "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": 18.48848807950653,
          "uncertainty": 43.288827977848925,
          "unilateral_faults": 0,
          "wins": 2
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 52,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 26,
          "draws": 47,
          "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": 3,
          "model": "moonshotai/kimi-k3",
          "point_rating_method": "sequential_elo",
          "public_id": "E-d3d3da42e99695b1",
          "rated_matches": 52,
          "raw_elo_rating": 1485.1516516180754,
          "reasoning": "low",
          "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": 24.003531501710604,
          "uncertainty": 24.930281974344517,
          "unilateral_faults": 0,
          "wins": 2
        },
        {
          "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": 1464.2426317683783,
          "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": 21.874533667805792,
          "uncertainty": 10.482614454664043,
          "unilateral_faults": 0,
          "wins": 2
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 32,
          "capped_draws": 0,
          "coverage_status": "under_covered",
          "distinct_rated_opponents": 16,
          "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": "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": 6,
          "model": "nvidia/nemotron-3-ultra-550b-a55b",
          "point_rating_method": "sequential_elo",
          "public_id": "E-2404d10bab26a254",
          "rated_matches": 32,
          "raw_elo_rating": 1461.4453871714331,
          "reasoning": "high",
          "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": 15.262238874634908,
          "uncertainty": 43.288827977848925,
          "unilateral_faults": 0,
          "wins": 0
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 34,
          "capped_draws": 0,
          "coverage_status": "under_covered",
          "distinct_rated_opponents": 17,
          "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": "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": 10,
          "model": "nvidia/nemotron-3-ultra-550b-a55b",
          "point_rating_method": "sequential_elo",
          "public_id": "E-abd2cae3e3ff9bdb",
          "rated_matches": 34,
          "raw_elo_rating": 1442.551306509627,
          "reasoning": "high",
          "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": 11.42007860588387,
          "uncertainty": 40.76542547285167,
          "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": "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": 88,
          "raw_elo_rating": 1463.2953460829026,
          "reasoning": "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": 21.883388248077022,
          "uncertainty": 9.249894000318006,
          "unilateral_faults": 0,
          "wins": 1
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 84,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 42,
          "draws": 75,
          "evaluated_setting_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": 84,
          "raw_elo_rating": 1482.281346131285,
          "reasoning": "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": 25.98156528887542,
          "uncertainty": 10.482614454664043,
          "unilateral_faults": 0,
          "wins": 4
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 32,
          "capped_draws": 0,
          "coverage_status": "under_covered",
          "distinct_rated_opponents": 16,
          "draws": 21,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "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-e5b4a3586049e1c9",
          "rated_matches": 32,
          "raw_elo_rating": 1412.4140830180731,
          "reasoning": "high",
          "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": 4.098853694911825,
          "uncertainty": 43.288827977848925,
          "unilateral_faults": 0,
          "wins": 0
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 16,
          "capped_draws": 0,
          "coverage_status": "under_covered",
          "distinct_rated_opponents": 7,
          "draws": 14,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "enabled",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "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": 0,
          "model": "poolside/laguna-s-2.1",
          "point_rating_method": "sequential_elo",
          "public_id": "E-7164ee63b9dd911a",
          "rated_matches": 14,
          "raw_elo_rating": 1497.5699603018195,
          "reasoning": "enabled",
          "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": 15.825989542536085,
          "uncertainty": 85.34944487358055,
          "unilateral_faults": 0,
          "wins": 0
        },
        {
          "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": "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": 0,
          "model": "poolside/laguna-s-2.1",
          "point_rating_method": "sequential_elo",
          "public_id": "E-ba56689188a301b2",
          "rated_matches": 18,
          "raw_elo_rating": 1492.882725737239,
          "reasoning": "enabled",
          "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": 17.380130896494958,
          "uncertainty": 70.95786693528086,
          "unilateral_faults": 0,
          "wins": 0
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 104,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 51,
          "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": "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": 104,
          "raw_elo_rating": 1474.448849917776,
          "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": 25.188695148003053,
          "uncertainty": 5.045003647426665,
          "unilateral_faults": 0,
          "wins": 3
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 76,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 38,
          "draws": 62,
          "evaluated_setting_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": 76,
          "raw_elo_rating": 1491.6324167926382,
          "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": 27.610135698210527,
          "uncertainty": 13.230288229818967,
          "unilateral_faults": 0,
          "wins": 8
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 48,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 24,
          "draws": 44,
          "evaluated_setting_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": 1,
          "model": "qwen/qwen3.7-max",
          "point_rating_method": "sequential_elo",
          "public_id": "E-95265340f8562bfd",
          "rated_matches": 48,
          "raw_elo_rating": 1498.2890155617906,
          "reasoning": "enabled",
          "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": 26.49404822461132,
          "uncertainty": 27.678571428571434,
          "unilateral_faults": 0,
          "wins": 3
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 90,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 44,
          "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": "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": 0,
          "model": "qwen/qwen3.7-plus",
          "point_rating_method": "sequential_elo",
          "public_id": "E-010dafcd7561851a",
          "rated_matches": 90,
          "raw_elo_rating": 1472.4062283762817,
          "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": 24.06441481400451,
          "uncertainty": 8.664241836095918,
          "unilateral_faults": 0,
          "wins": 0
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 54,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 27,
          "draws": 49,
          "evaluated_setting_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": 54,
          "raw_elo_rating": 1487.9660769853413,
          "reasoning": "enabled",
          "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": 24.87387032897688,
          "uncertainty": 23.66998624632421,
          "unilateral_faults": 0,
          "wins": 1
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 84,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 42,
          "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": "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": 84,
          "raw_elo_rating": 1483.647195989816,
          "reasoning": "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": 26.292540253374842,
          "uncertainty": 10.482614454664043,
          "unilateral_faults": 0,
          "wins": 1
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 70,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 35,
          "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": "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": 70,
          "raw_elo_rating": 1454.0917807935598,
          "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": 18.633293372543374,
          "uncertainty": 15.58908290969266,
          "unilateral_faults": 0,
          "wins": 0
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 30,
          "capped_draws": 0,
          "coverage_status": "under_covered",
          "distinct_rated_opponents": 14,
          "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": "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": 11,
          "model": "tencent/hy3-preview",
          "point_rating_method": "sequential_elo",
          "public_id": "E-fbf6af15f65f01d7",
          "rated_matches": 28,
          "raw_elo_rating": 1399.058360252803,
          "reasoning": "high",
          "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": 0.0,
          "uncertainty": 49.09766908852594,
          "unilateral_faults": 2,
          "wins": 0
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 100,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 49,
          "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": "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": 100,
          "raw_elo_rating": 1496.1585038473304,
          "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": 29.957237052457256,
          "uncertainty": 6.001859510499461,
          "unilateral_faults": 0,
          "wins": 2
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 16,
          "capped_draws": 0,
          "coverage_status": "under_covered",
          "distinct_rated_opponents": 7,
          "draws": 13,
          "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": 0,
          "model": "thinkingmachines/inkling",
          "point_rating_method": "sequential_elo",
          "public_id": "E-9468e854340a4e9b",
          "rated_matches": 14,
          "raw_elo_rating": 1491.1086378377042,
          "reasoning": "max",
          "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": 14.354883833993085,
          "uncertainty": 85.34944487358055,
          "unilateral_faults": 0,
          "wins": 1
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 32,
          "capped_draws": 0,
          "coverage_status": "under_covered",
          "distinct_rated_opponents": 16,
          "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": "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": 8,
          "model": "x-ai/grok-4.5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-0576181f89efa7a7",
          "rated_matches": 32,
          "raw_elo_rating": 1522.169443824012,
          "reasoning": "high",
          "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": 29.0878151221639,
          "uncertainty": 43.288827977848925,
          "unilateral_faults": 0,
          "wins": 8
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 38,
          "capped_draws": 0,
          "coverage_status": "under_covered",
          "distinct_rated_opponents": 19,
          "draws": 31,
          "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": 5,
          "model": "x-ai/grok-4.5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-88ab68f664bd3ea0",
          "rated_matches": 38,
          "raw_elo_rating": 1486.799452161452,
          "reasoning": "low",
          "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": 22.305222241021823,
          "uncertainty": 36.31407690254356,
          "unilateral_faults": 0,
          "wins": 2
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 96,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 48,
          "draws": 67,
          "evaluated_setting_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": 96,
          "raw_elo_rating": 1499.1232344259092,
          "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": 30.44728628591251,
          "uncertainty": 7.017308256680951,
          "unilateral_faults": 0,
          "wins": 13
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 54,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 27,
          "draws": 49,
          "evaluated_setting_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": 54,
          "raw_elo_rating": 1482.2015752361406,
          "reasoning": "enabled",
          "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": 23.56141587754649,
          "uncertainty": 23.66998624632421,
          "unilateral_faults": 0,
          "wins": 2
        },
        {
          "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": "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": 64,
          "raw_elo_rating": 1474.2125218481146,
          "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": 22.726527476576994,
          "uncertainty": 18.26736729460423,
          "unilateral_faults": 0,
          "wins": 0
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 50,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 25,
          "draws": 45,
          "evaluated_setting_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": 3,
          "model": "xiaomi/mimo-v2.5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-5b213ae773e821cc",
          "rated_matches": 50,
          "raw_elo_rating": 1490.3044220858997,
          "reasoning": "enabled",
          "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": 24.93377960152974,
          "uncertainty": 26.264004201400486,
          "unilateral_faults": 0,
          "wins": 2
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 70,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 35,
          "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": "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": 70,
          "raw_elo_rating": 1505.0662350094012,
          "reasoning": "high",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "repaired",
          "score": 30.2390924954411,
          "uncertainty": 15.58908290969266,
          "unilateral_faults": 0,
          "wins": 3
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 46,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 23,
          "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": "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": 3,
          "model": "xiaomi/mimo-v2.5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-a5f372b0e5962ee5",
          "rated_matches": 46,
          "raw_elo_rating": 1466.195547247045,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "repaired",
          "score": 18.913118772607746,
          "uncertainty": 29.182495748947275,
          "unilateral_faults": 0,
          "wins": 0
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 46,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 23,
          "draws": 39,
          "evaluated_setting_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": 5,
          "model": "xiaomi/mimo-v2.5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-c37f25e181320efb",
          "rated_matches": 46,
          "raw_elo_rating": 1486.8182780372601,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "repaired",
          "score": 23.608475978461932,
          "uncertainty": 29.182495748947275,
          "unilateral_faults": 0,
          "wins": 2
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 76,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 38,
          "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": "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": 76,
          "raw_elo_rating": 1499.0331584380926,
          "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": 29.295127175194555,
          "uncertainty": 13.230288229818967,
          "unilateral_faults": 0,
          "wins": 5
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 62,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 31,
          "draws": 61,
          "evaluated_setting_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": 62,
          "raw_elo_rating": 1475.841977949159,
          "reasoning": "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": 22.919618819874938,
          "uncertainty": 19.244078834871203,
          "unilateral_faults": 0,
          "wins": 0
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 64,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 32,
          "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": "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": 5,
          "model": "z-ai/glm-5.2",
          "point_rating_method": "sequential_elo",
          "public_id": "E-4959351a96fd2b82",
          "rated_matches": 64,
          "raw_elo_rating": 1452.3700253768327,
          "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": 17.75345556657859,
          "uncertainty": 18.26736729460423,
          "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": 1478.1676330281302,
          "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": 23.44912102035759,
          "uncertainty": 19.244078834871203,
          "unilateral_faults": 0,
          "wins": 1
        }
      ],
      "GB2-03": [
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 64,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 29,
          "draws": 30,
          "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": 64,
          "raw_elo_rating": 1700.3473191690596,
          "reasoning": "xhigh",
          "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": 70.49045424400458,
          "uncertainty": 18.26736729460423,
          "unilateral_faults": 0,
          "wins": 27
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 88,
          "capped_draws": 13,
          "coverage_status": "rated",
          "distinct_rated_opponents": 44,
          "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-4-5",
            "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": 88,
          "raw_elo_rating": 1518.8257098927816,
          "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": 43.90185636252289,
          "uncertainty": 9.249894000318006,
          "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": "legacy_shared_thinking_budget",
          "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": 24,
          "capped_draws": 1,
          "coverage_status": "under_covered",
          "distinct_rated_opponents": 12,
          "draws": 6,
          "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": 14,
          "model": "claude-opus-4-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-d5810442d7094396",
          "rated_matches": 24,
          "raw_elo_rating": 1384.726716888602,
          "reasoning": "high",
          "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": 17.7111628193571,
          "uncertainty": 56.25,
          "unilateral_faults": 0,
          "wins": 4
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 68,
          "capped_draws": 10,
          "coverage_status": "rated",
          "distinct_rated_opponents": 34,
          "draws": 34,
          "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": 22,
          "model": "claude-opus-4-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-dfb18dba94eee30b",
          "rated_matches": 68,
          "raw_elo_rating": 1438.7975158584218,
          "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": 30.81671727920589,
          "uncertainty": 16.4429265428846,
          "unilateral_faults": 0,
          "wins": 12
        },
        {
          "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": 1449.778133454939,
          "reasoning": "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": 32.26904479710366,
          "uncertainty": 18.26736729460423,
          "unilateral_faults": 0,
          "wins": 11
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 56,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 24,
          "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": 56,
          "raw_elo_rating": 1897.1712916753029,
          "reasoning": "xhigh",
          "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": 22.47661785325219,
          "unilateral_faults": 0,
          "wins": 52
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 84,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 42,
          "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": 31,
          "model": "claude-opus-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-49aaba66f6b19080",
          "rated_matches": 84,
          "raw_elo_rating": 1647.928081769382,
          "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": 63.44448907504303,
          "uncertainty": 10.482614454664043,
          "unilateral_faults": 0,
          "wins": 42
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 56,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 24,
          "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": 56,
          "raw_elo_rating": 1875.9966416414663,
          "reasoning": "xhigh",
          "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": 96.77005388139995,
          "uncertainty": 22.47661785325219,
          "unilateral_faults": 0,
          "wins": 51
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 78,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 39,
          "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": 78,
          "raw_elo_rating": 1840.6237701972532,
          "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": 92.59125164361666,
          "uncertainty": 12.5043950463012,
          "unilateral_faults": 0,
          "wins": 64
        },
        {
          "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": 5,
          "model": "claude-opus-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-d8babc5495b1a188",
          "rated_matches": 80,
          "raw_elo_rating": 1881.3828904374436,
          "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": 98.89386033488782,
          "uncertainty": 11.805555555555554,
          "unilateral_faults": 0,
          "wins": 71
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 88,
          "capped_draws": 1,
          "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-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": 23,
          "model": "claude-opus-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-ecf847457e616425",
          "rated_matches": 88,
          "raw_elo_rating": 1524.3683554934487,
          "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": 44.74732236153788,
          "uncertainty": 9.249894000318006,
          "unilateral_faults": 0,
          "wins": 42
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 76,
          "capped_draws": 1,
          "coverage_status": "rated",
          "distinct_rated_opponents": 35,
          "draws": 36,
          "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": 76,
          "raw_elo_rating": 1595.279480462201,
          "reasoning": "xhigh",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_7fad32_to_brackets_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "xhigh",
          "repair_status": "first_pass",
          "score": 55.078257956466814,
          "uncertainty": 13.230288229818967,
          "unilateral_faults": 0,
          "wins": 24
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 98,
          "capped_draws": 3,
          "coverage_status": "rated",
          "distinct_rated_opponents": 45,
          "draws": 34,
          "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": 32,
          "model": "claude-sonnet-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-d49e8df479ed0377",
          "rated_matches": 98,
          "raw_elo_rating": 1552.5070357171141,
          "reasoning": "xhigh",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_7fad32_to_brackets_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "xhigh",
          "repair_status": "first_pass",
          "score": 49.374890832643544,
          "uncertainty": 6.501890762960602,
          "unilateral_faults": 0,
          "wins": 32
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 32,
          "capped_draws": 1,
          "coverage_status": "under_covered",
          "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": 1392.6036728774286,
          "reasoning": "enabled",
          "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": 20.494361273200912,
          "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": 1524.4985638630642,
          "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": 43.00749050094252,
          "uncertainty": 23.66998624632421,
          "unilateral_faults": 0,
          "wins": 15
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 86,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 43,
          "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": "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": 27,
          "model": "deepseek/deepseek-v4-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-ae9d59ec3a8a1d63",
          "rated_matches": 86,
          "raw_elo_rating": 1438.523896395089,
          "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": 31.578832477807513,
          "uncertainty": 9.855626741889738,
          "unilateral_faults": 0,
          "wins": 20
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 62,
          "capped_draws": 1,
          "coverage_status": "rated",
          "distinct_rated_opponents": 29,
          "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": 62,
          "raw_elo_rating": 1406.28947900497,
          "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": 25.516168554327326,
          "uncertainty": 19.244078834871203,
          "unilateral_faults": 0,
          "wins": 15
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 38,
          "capped_draws": 1,
          "coverage_status": "under_covered",
          "distinct_rated_opponents": 19,
          "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",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_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": "google/gemini-3.5-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-46c3bb79de67d970",
          "rated_matches": 38,
          "raw_elo_rating": 1480.0032664035127,
          "reasoning": "high",
          "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": 34.67728441611023,
          "uncertainty": 36.31407690254356,
          "unilateral_faults": 0,
          "wins": 6
        },
        {
          "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": 1571.8753694864479,
          "reasoning": "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": 51.11619311992135,
          "uncertainty": 16.4429265428846,
          "unilateral_faults": 0,
          "wins": 23
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 34,
          "capped_draws": 1,
          "coverage_status": "under_covered",
          "distinct_rated_opponents": 17,
          "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": "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": 7,
          "model": "google/gemini-3.5-flash-lite",
          "point_rating_method": "sequential_elo",
          "public_id": "E-28274045fbc35ae9",
          "rated_matches": 34,
          "raw_elo_rating": 1548.3739228344587,
          "reasoning": "minimal",
          "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": 44.56323026177964,
          "uncertainty": 40.76542547285167,
          "unilateral_faults": 0,
          "wins": 13
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 24,
          "capped_draws": 0,
          "coverage_status": "under_covered",
          "distinct_rated_opponents": 12,
          "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": "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": 11,
          "model": "google/gemini-3.5-flash-lite",
          "point_rating_method": "sequential_elo",
          "public_id": "E-7ed90f1b43d80cf9",
          "rated_matches": 24,
          "raw_elo_rating": 1505.3722146616713,
          "reasoning": "high",
          "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": 36.1142276462138,
          "uncertainty": 56.25,
          "unilateral_faults": 0,
          "wins": 10
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 52,
          "capped_draws": 2,
          "coverage_status": "rated",
          "distinct_rated_opponents": 26,
          "draws": 19,
          "evaluated_setting_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": 22,
          "model": "google/gemini-3.5-flash-lite",
          "point_rating_method": "sequential_elo",
          "public_id": "E-c7e8525629d5d658",
          "rated_matches": 52,
          "raw_elo_rating": 1450.3211376075822,
          "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": 31.53879375886739,
          "uncertainty": 24.930281974344517,
          "unilateral_faults": 0,
          "wins": 11
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 24,
          "capped_draws": 1,
          "coverage_status": "under_covered",
          "distinct_rated_opponents": 12,
          "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": "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": 11,
          "model": "google/gemini-3.5-flash-lite",
          "point_rating_method": "sequential_elo",
          "public_id": "E-d485651284072880",
          "rated_matches": 24,
          "raw_elo_rating": 1464.0261492484403,
          "reasoning": "high",
          "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": 29.807367165051325,
          "uncertainty": 56.25,
          "unilateral_faults": 0,
          "wins": 6
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 52,
          "capped_draws": 6,
          "coverage_status": "rated",
          "distinct_rated_opponents": 26,
          "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-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-d9a1854998f1794f",
          "rated_matches": 52,
          "raw_elo_rating": 1419.4269463569747,
          "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": 26.82624488756462,
          "uncertainty": 24.930281974344517,
          "unilateral_faults": 0,
          "wins": 7
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 50,
          "capped_draws": 1,
          "coverage_status": "rated",
          "distinct_rated_opponents": 25,
          "draws": 14,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "medium",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "google/gemini-3.6-flash",
            "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 16,
          "model": "google/gemini-3.6-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-1d4a922c11c37a8d",
          "rated_matches": 50,
          "raw_elo_rating": 1516.2025080152273,
          "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": 41.425474084503904,
          "uncertainty": 26.264004201400486,
          "unilateral_faults": 0,
          "wins": 20
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 45,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 23,
          "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": "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": 20,
          "model": "google/gemini-3.6-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-2e4f025f94dafe33",
          "rated_matches": 45,
          "raw_elo_rating": 1432.79675175012,
          "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": 28.250533342732655,
          "uncertainty": 29.97097807744857,
          "unilateral_faults": 0,
          "wins": 12
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 34,
          "capped_draws": 2,
          "coverage_status": "under_covered",
          "distinct_rated_opponents": 17,
          "draws": 8,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "minimal",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "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-6743f1c221046d65",
          "rated_matches": 34,
          "raw_elo_rating": 1590.360541675656,
          "reasoning": "minimal",
          "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": 50.96779970413437,
          "uncertainty": 40.76542547285167,
          "unilateral_faults": 0,
          "wins": 18
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 34,
          "capped_draws": 2,
          "coverage_status": "under_covered",
          "distinct_rated_opponents": 17,
          "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": "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-80b8c1a18d6dd238",
          "rated_matches": 34,
          "raw_elo_rating": 1511.5768806057672,
          "reasoning": "minimal",
          "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": 38.95027025853986,
          "uncertainty": 40.76542547285167,
          "unilateral_faults": 0,
          "wins": 11
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 26,
          "capped_draws": 0,
          "coverage_status": "under_covered",
          "distinct_rated_opponents": 13,
          "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": "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-97580ecf1bd06d40",
          "rated_matches": 26,
          "raw_elo_rating": 1602.1008415430224,
          "reasoning": "high",
          "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": 51.32971285079575,
          "uncertainty": 52.475044864937615,
          "unilateral_faults": 0,
          "wins": 15
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 82,
          "capped_draws": 2,
          "coverage_status": "rated",
          "distinct_rated_opponents": 41,
          "draws": 27,
          "evaluated_setting_identity": {
            "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": 30,
          "model": "gpt-4.1",
          "point_rating_method": "sequential_elo",
          "public_id": "E-c7da9914f86ee846",
          "rated_matches": 82,
          "raw_elo_rating": 1525.8397181307937,
          "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": 44.74207105225406,
          "uncertainty": 11.132129994845172,
          "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": "low",
          "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": 29,
          "capped_draws": 1,
          "coverage_status": "under_covered",
          "distinct_rated_opponents": 14,
          "draws": 8,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 14,
          "model": "gpt-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-cc568b7069d5a0fd",
          "rated_matches": 28,
          "raw_elo_rating": 1399.4380048256987,
          "reasoning": "high",
          "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": 20.82800215505983,
          "uncertainty": 49.09766908852594,
          "unilateral_faults": 1,
          "wins": 6
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 62,
          "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": 62,
          "raw_elo_rating": 1399.3895422530882,
          "reasoning": "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": 24.46366360644326,
          "uncertainty": 19.244078834871203,
          "unilateral_faults": 0,
          "wins": 8
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 78,
          "capped_draws": 2,
          "coverage_status": "rated",
          "distinct_rated_opponents": 39,
          "draws": 36,
          "evaluated_setting_identity": {
            "canonical_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": 24,
          "model": "gpt-5.4",
          "point_rating_method": "sequential_elo",
          "public_id": "E-496f83ad0bd69447",
          "rated_matches": 78,
          "raw_elo_rating": 1439.39286064408,
          "reasoning": "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": 31.388151856713836,
          "uncertainty": 12.5043950463012,
          "unilateral_faults": 0,
          "wins": 18
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 60,
          "capped_draws": 7,
          "coverage_status": "rated",
          "distinct_rated_opponents": 29,
          "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": 24,
          "model": "gpt-5.4",
          "point_rating_method": "sequential_elo",
          "public_id": "E-4b75acaf58f14113",
          "rated_matches": 58,
          "raw_elo_rating": 1449.7947632570085,
          "reasoning": "xhigh",
          "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": 31.89608232157542,
          "uncertainty": 21.344455490411935,
          "unilateral_faults": 2,
          "wins": 17
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 80,
          "capped_draws": 4,
          "coverage_status": "rated",
          "distinct_rated_opponents": 40,
          "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": 80,
          "raw_elo_rating": 1602.3083636563829,
          "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": 56.324293275397885,
          "uncertainty": 11.805555555555554,
          "unilateral_faults": 0,
          "wins": 31
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 82,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 41,
          "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": 4,
          "model": "gpt-5.4-mini",
          "point_rating_method": "sequential_elo",
          "public_id": "E-35117a2e624d7970",
          "rated_matches": 82,
          "raw_elo_rating": 1480.7237122491786,
          "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": 37.860150083019626,
          "uncertainty": 11.132129994845172,
          "unilateral_faults": 0,
          "wins": 1
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 83,
          "capped_draws": 11,
          "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-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": 20,
          "model": "gpt-5.4-mini",
          "point_rating_method": "sequential_elo",
          "public_id": "E-9e39bdd48b7328c7",
          "rated_matches": 83,
          "raw_elo_rating": 1485.5548858435868,
          "reasoning": "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": 38.63707357709248,
          "uncertainty": 10.804472558998102,
          "unilateral_faults": 0,
          "wins": 15
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 88,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 44,
          "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-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": 88,
          "raw_elo_rating": 1508.3524419563448,
          "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": 42.304281381765435,
          "uncertainty": 9.249894000318006,
          "unilateral_faults": 0,
          "wins": 28
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 80,
          "capped_draws": 7,
          "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-5.5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_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-5.5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-446036823932df16",
          "rated_matches": 80,
          "raw_elo_rating": 1453.647103601243,
          "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": 33.64775037461809,
          "uncertainty": 11.805555555555554,
          "unilateral_faults": 0,
          "wins": 18
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 74,
          "capped_draws": 7,
          "coverage_status": "rated",
          "distinct_rated_opponents": 37,
          "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-5.5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_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": 74,
          "raw_elo_rating": 1440.3708349548044,
          "reasoning": "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": 31.35664793074286,
          "uncertainty": 13.985026918962571,
          "unilateral_faults": 0,
          "wins": 15
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 81,
          "capped_draws": 3,
          "coverage_status": "rated",
          "distinct_rated_opponents": 40,
          "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": 80,
          "raw_elo_rating": 1530.3839322567405,
          "reasoning": "xhigh",
          "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": 45.35305938673562,
          "uncertainty": 11.805555555555554,
          "unilateral_faults": 0,
          "wins": 21
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 70,
          "capped_draws": 13,
          "coverage_status": "rated",
          "distinct_rated_opponents": 35,
          "draws": 42,
          "evaluated_setting_identity": {
            "canonical_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": 70,
          "raw_elo_rating": 1449.241069098968,
          "reasoning": "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": 32.513954746621025,
          "uncertainty": 15.58908290969266,
          "unilateral_faults": 0,
          "wins": 11
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 64,
          "capped_draws": 2,
          "coverage_status": "rated",
          "distinct_rated_opponents": 31,
          "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": 64,
          "raw_elo_rating": 1341.726476188212,
          "reasoning": "xhigh",
          "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": 15.787023585925473,
          "uncertainty": 18.26736729460423,
          "unilateral_faults": 0,
          "wins": 6
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 76,
          "capped_draws": 1,
          "coverage_status": "rated",
          "distinct_rated_opponents": 37,
          "draws": 37,
          "evaluated_setting_identity": {
            "canonical_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-d192bb239087b778",
          "rated_matches": 76,
          "raw_elo_rating": 1476.915508520607,
          "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": 37.02321330902676,
          "uncertainty": 13.230288229818967,
          "unilateral_faults": 0,
          "wins": 21
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 68,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 29,
          "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": 68,
          "raw_elo_rating": 1616.3799977137346,
          "reasoning": "xhigh",
          "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": 57.90485555225239,
          "uncertainty": 16.4429265428846,
          "unilateral_faults": 0,
          "wins": 35
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 80,
          "capped_draws": 14,
          "coverage_status": "rated",
          "distinct_rated_opponents": 40,
          "draws": 41,
          "evaluated_setting_identity": {
            "canonical_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": 24,
          "model": "gpt-5.6-sol",
          "point_rating_method": "sequential_elo",
          "public_id": "E-527999604d620080",
          "rated_matches": 80,
          "raw_elo_rating": 1451.199816272659,
          "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": 33.27444521040391,
          "uncertainty": 11.805555555555554,
          "unilateral_faults": 0,
          "wins": 15
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 58,
          "capped_draws": 2,
          "coverage_status": "rated",
          "distinct_rated_opponents": 29,
          "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": 58,
          "raw_elo_rating": 1545.0279839646837,
          "reasoning": "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": 46.42280040640819,
          "uncertainty": 21.344455490411935,
          "unilateral_faults": 0,
          "wins": 29
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 58,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 27,
          "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": 58,
          "raw_elo_rating": 1584.7107585816805,
          "reasoning": "xhigh",
          "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": 52.47594525860797,
          "uncertainty": 21.344455490411935,
          "unilateral_faults": 0,
          "wins": 27
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 78,
          "capped_draws": 8,
          "coverage_status": "rated",
          "distinct_rated_opponents": 39,
          "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-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": 23,
          "model": "gpt-5.6-terra",
          "point_rating_method": "sequential_elo",
          "public_id": "E-c2f0f8f062659e83",
          "rated_matches": 78,
          "raw_elo_rating": 1525.7262366492885,
          "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": 44.55730234033761,
          "uncertainty": 12.5043950463012,
          "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": 1484.2886571135925,
          "reasoning": "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": 38.23648244618929,
          "uncertainty": 12.5043950463012,
          "unilateral_faults": 0,
          "wins": 14
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 100,
          "capped_draws": 1,
          "coverage_status": "rated",
          "distinct_rated_opponents": 41,
          "draws": 39,
          "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": 100,
          "raw_elo_rating": 1327.6233920315324,
          "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": 15.132530666228146,
          "uncertainty": 6.001859510499461,
          "unilateral_faults": 0,
          "wins": 14
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 96,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 39,
          "draws": 45,
          "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": 96,
          "raw_elo_rating": 1440.3263728765553,
          "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": 32.20014118958681,
          "uncertainty": 7.017308256680951,
          "unilateral_faults": 0,
          "wins": 21
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 78,
          "capped_draws": 5,
          "coverage_status": "rated",
          "distinct_rated_opponents": 37,
          "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": 32,
          "model": "meituan/longcat-2.0",
          "point_rating_method": "sequential_elo",
          "public_id": "E-198e8ddfe9f7ce20",
          "rated_matches": 78,
          "raw_elo_rating": 1348.6392568902086,
          "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": 17.54474713808228,
          "uncertainty": 12.5043950463012,
          "unilateral_faults": 0,
          "wins": 11
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 84,
          "capped_draws": 9,
          "coverage_status": "rated",
          "distinct_rated_opponents": 40,
          "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": 19,
          "model": "meituan/longcat-2.0",
          "point_rating_method": "sequential_elo",
          "public_id": "E-84709c769628f9a2",
          "rated_matches": 84,
          "raw_elo_rating": 1472.8951815703904,
          "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": 36.74525977389118,
          "uncertainty": 10.482614454664043,
          "unilateral_faults": 0,
          "wins": 26
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 32,
          "capped_draws": 2,
          "coverage_status": "under_covered",
          "distinct_rated_opponents": 16,
          "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": "meituan/longcat-2.0",
            "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 7,
          "model": "meituan/longcat-2.0",
          "point_rating_method": "sequential_elo",
          "public_id": "E-d3a5befe76215b48",
          "rated_matches": 32,
          "raw_elo_rating": 1523.8698064263606,
          "reasoning": "enabled",
          "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": 40.517480327470835,
          "uncertainty": 43.288827977848925,
          "unilateral_faults": 0,
          "wins": 12
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 90,
          "capped_draws": 1,
          "coverage_status": "rated",
          "distinct_rated_opponents": 45,
          "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": "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": 25,
          "model": "minimax/minimax-m3",
          "point_rating_method": "sequential_elo",
          "public_id": "E-44cc758f104a74ab",
          "rated_matches": 90,
          "raw_elo_rating": 1480.8755147233076,
          "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": 38.18446384616218,
          "uncertainty": 8.664241836095918,
          "unilateral_faults": 0,
          "wins": 32
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 38,
          "capped_draws": 0,
          "coverage_status": "under_covered",
          "distinct_rated_opponents": 19,
          "draws": 7,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "low",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "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": 3,
          "model": "moonshotai/kimi-k3",
          "point_rating_method": "sequential_elo",
          "public_id": "E-09859be1b47131a0",
          "rated_matches": 38,
          "raw_elo_rating": 1710.1148854952874,
          "reasoning": "low",
          "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": 69.77813046280103,
          "uncertainty": 36.31407690254356,
          "unilateral_faults": 0,
          "wins": 28
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 26,
          "capped_draws": 0,
          "coverage_status": "under_covered",
          "distinct_rated_opponents": 13,
          "draws": 11,
          "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": 9,
          "model": "moonshotai/kimi-k3",
          "point_rating_method": "sequential_elo",
          "public_id": "E-8f139a9e4d538859",
          "rated_matches": 26,
          "raw_elo_rating": 1498.1810215922073,
          "reasoning": "max",
          "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": 35.477955274666584,
          "uncertainty": 52.475044864937615,
          "unilateral_faults": 0,
          "wins": 6
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 34,
          "capped_draws": 1,
          "coverage_status": "under_covered",
          "distinct_rated_opponents": 17,
          "draws": 14,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "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": 6,
          "model": "moonshotai/kimi-k3",
          "point_rating_method": "sequential_elo",
          "public_id": "E-980b1f419104e27a",
          "rated_matches": 34,
          "raw_elo_rating": 1597.8931533577227,
          "reasoning": "high",
          "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": 52.11681184018075,
          "uncertainty": 40.76542547285167,
          "unilateral_faults": 0,
          "wins": 14
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 36,
          "capped_draws": 2,
          "coverage_status": "under_covered",
          "distinct_rated_opponents": 18,
          "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": "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": 13,
          "model": "nex-agi/nex-n2-pro",
          "point_rating_method": "sequential_elo",
          "public_id": "E-57ad2863cbf32d58",
          "rated_matches": 36,
          "raw_elo_rating": 1436.5490406123818,
          "reasoning": "enabled",
          "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": 27.788262281969292,
          "uncertainty": 38.449493652678655,
          "unilateral_faults": 0,
          "wins": 5
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 66,
          "capped_draws": 7,
          "coverage_status": "rated",
          "distinct_rated_opponents": 31,
          "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": 14,
          "model": "nex-agi/nex-n2-pro",
          "point_rating_method": "sequential_elo",
          "public_id": "E-a05d4cef5f788f16",
          "rated_matches": 66,
          "raw_elo_rating": 1450.3899699523217,
          "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": 32.476184640834816,
          "uncertainty": 17.33472217815261,
          "unilateral_faults": 0,
          "wins": 9
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 48,
          "capped_draws": 6,
          "coverage_status": "rated",
          "distinct_rated_opponents": 24,
          "draws": 36,
          "evaluated_setting_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": 48,
          "raw_elo_rating": 1414.2361193788938,
          "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": 25.69906909498186,
          "uncertainty": 27.678571428571434,
          "unilateral_faults": 0,
          "wins": 3
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 26,
          "capped_draws": 1,
          "coverage_status": "under_covered",
          "distinct_rated_opponents": 12,
          "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": "o3",
            "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-03T16:00:00Z",
          "losses": 8,
          "model": "o3",
          "point_rating_method": "sequential_elo",
          "public_id": "E-9f7b8b1adc2ddba7",
          "rated_matches": 24,
          "raw_elo_rating": 1459.4837652461133,
          "reasoning": "high",
          "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": 29.11447941701005,
          "uncertainty": 56.25,
          "unilateral_faults": 0,
          "wins": 7
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 62,
          "capped_draws": 8,
          "coverage_status": "rated",
          "distinct_rated_opponents": 31,
          "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": 11,
          "model": "openai/gpt-oss-120b",
          "point_rating_method": "sequential_elo",
          "public_id": "E-87b4bd61da369b42",
          "rated_matches": 62,
          "raw_elo_rating": 1430.255627323167,
          "reasoning": "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": 29.171925207422163,
          "uncertainty": 19.244078834871203,
          "unilateral_faults": 0,
          "wins": 8
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 44,
          "capped_draws": 2,
          "coverage_status": "rated",
          "distinct_rated_opponents": 22,
          "draws": 28,
          "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": 13,
          "model": "openai/gpt-oss-120b",
          "point_rating_method": "sequential_elo",
          "public_id": "E-c90a449ff5e7b79a",
          "rated_matches": 44,
          "raw_elo_rating": 1380.5301299249386,
          "reasoning": "low",
          "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": 20.17846046223821,
          "uncertainty": 30.785599249992988,
          "unilateral_faults": 0,
          "wins": 3
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 26,
          "capped_draws": 1,
          "coverage_status": "under_covered",
          "distinct_rated_opponents": 13,
          "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": "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-08762a3df1a52f6b",
          "rated_matches": 26,
          "raw_elo_rating": 1462.487607959199,
          "reasoning": "enabled",
          "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": 30.033340953329773,
          "uncertainty": 52.475044864937615,
          "unilateral_faults": 0,
          "wins": 3
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 70,
          "capped_draws": 1,
          "coverage_status": "rated",
          "distinct_rated_opponents": 35,
          "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": "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": 18,
          "model": "poolside/laguna-s-2.1",
          "point_rating_method": "sequential_elo",
          "public_id": "E-7acc466aeae25d41",
          "rated_matches": 70,
          "raw_elo_rating": 1463.857478465486,
          "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": 34.74351767331942,
          "uncertainty": 15.58908290969266,
          "unilateral_faults": 0,
          "wins": 19
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 86,
          "capped_draws": 5,
          "coverage_status": "rated",
          "distinct_rated_opponents": 43,
          "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": "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": 86,
          "raw_elo_rating": 1445.8680017614674,
          "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": 32.69909017202293,
          "uncertainty": 9.855626741889738,
          "unilateral_faults": 0,
          "wins": 20
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 26,
          "capped_draws": 2,
          "coverage_status": "under_covered",
          "distinct_rated_opponents": 13,
          "draws": 6,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "enabled",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "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": 11,
          "model": "poolside/laguna-s-2.1",
          "point_rating_method": "sequential_elo",
          "public_id": "E-936fb7956df3d03b",
          "rated_matches": 26,
          "raw_elo_rating": 1506.5582599696256,
          "reasoning": "enabled",
          "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": 36.7558053708189,
          "uncertainty": 52.475044864937615,
          "unilateral_faults": 0,
          "wins": 9
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 66,
          "capped_draws": 6,
          "coverage_status": "rated",
          "distinct_rated_opponents": 31,
          "draws": 50,
          "evaluated_setting_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": 66,
          "raw_elo_rating": 1437.7587628203037,
          "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": 30.549441181835455,
          "uncertainty": 17.33472217815261,
          "unilateral_faults": 0,
          "wins": 6
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 84,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 41,
          "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": "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": 84,
          "raw_elo_rating": 1450.2133962405546,
          "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": 33.28541772823972,
          "uncertainty": 10.482614454664043,
          "unilateral_faults": 0,
          "wins": 29
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 46,
          "capped_draws": 2,
          "coverage_status": "rated",
          "distinct_rated_opponents": 23,
          "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": "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": 14,
          "model": "thinkingmachines/inkling",
          "point_rating_method": "sequential_elo",
          "public_id": "E-77829668b3641188",
          "rated_matches": 46,
          "raw_elo_rating": 1607.1778209283398,
          "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": 54.946552450271184,
          "uncertainty": 29.182495748947275,
          "unilateral_faults": 0,
          "wins": 24
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 78,
          "capped_draws": 6,
          "coverage_status": "rated",
          "distinct_rated_opponents": 37,
          "draws": 42,
          "evaluated_setting_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": 78,
          "raw_elo_rating": 1450.0176958204406,
          "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": 33.00884665373824,
          "uncertainty": 12.5043950463012,
          "unilateral_faults": 0,
          "wins": 18
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 86,
          "capped_draws": 9,
          "coverage_status": "rated",
          "distinct_rated_opponents": 43,
          "draws": 36,
          "evaluated_setting_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": 86,
          "raw_elo_rating": 1603.7282506860715,
          "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": 56.77883163081865,
          "uncertainty": 9.855626741889738,
          "unilateral_faults": 0,
          "wins": 31
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 26,
          "capped_draws": 0,
          "coverage_status": "under_covered",
          "distinct_rated_opponents": 13,
          "draws": 11,
          "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-f9259c1ced4fba75",
          "rated_matches": 26,
          "raw_elo_rating": 1476.4317562753513,
          "reasoning": "max",
          "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": 32.16035829052158,
          "uncertainty": 52.475044864937615,
          "unilateral_faults": 0,
          "wins": 6
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 40,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 20,
          "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": "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-02f7e54245bd5c85",
          "rated_matches": 40,
          "raw_elo_rating": 1339.5741281314313,
          "reasoning": "low",
          "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": 13.497734328869447,
          "uncertainty": 34.33688094430304,
          "unilateral_faults": 0,
          "wins": 3
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 34,
          "capped_draws": 3,
          "coverage_status": "under_covered",
          "distinct_rated_opponents": 17,
          "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": "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": 11,
          "model": "x-ai/grok-4.5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-c0c60ca46f3ce498",
          "rated_matches": 34,
          "raw_elo_rating": 1432.2090815157947,
          "reasoning": "high",
          "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": 26.84363736482782,
          "uncertainty": 40.76542547285167,
          "unilateral_faults": 0,
          "wins": 5
        },
        {
          "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": 1504.1234121905509,
          "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": 41.26204320265185,
          "uncertainty": 12.5043950463012,
          "unilateral_faults": 0,
          "wins": 24
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 36,
          "capped_draws": 0,
          "coverage_status": "under_covered",
          "distinct_rated_opponents": 18,
          "draws": 19,
          "evaluated_setting_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": 9,
          "model": "x-ai/grok-build-0.1",
          "point_rating_method": "sequential_elo",
          "public_id": "E-2a93343a8a88fd59",
          "rated_matches": 36,
          "raw_elo_rating": 1486.663450518995,
          "reasoning": "enabled",
          "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": 35.4326315397912,
          "uncertainty": 38.449493652678655,
          "unilateral_faults": 0,
          "wins": 8
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 86,
          "capped_draws": 1,
          "coverage_status": "rated",
          "distinct_rated_opponents": 43,
          "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": 86,
          "raw_elo_rating": 1463.1084595149894,
          "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": 35.328921102635334,
          "uncertainty": 9.855626741889738,
          "unilateral_faults": 0,
          "wins": 19
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 68,
          "capped_draws": 5,
          "coverage_status": "rated",
          "distinct_rated_opponents": 32,
          "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": "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": 68,
          "raw_elo_rating": 1453.3589845100641,
          "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": 33.0378996400634,
          "uncertainty": 16.4429265428846,
          "unilateral_faults": 0,
          "wins": 14
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 52,
          "capped_draws": 13,
          "coverage_status": "rated",
          "distinct_rated_opponents": 26,
          "draws": 38,
          "evaluated_setting_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": 52,
          "raw_elo_rating": 1446.0068426521739,
          "reasoning": "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": 30.880698337056444,
          "uncertainty": 24.930281974344517,
          "unilateral_faults": 0,
          "wins": 3
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 54,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 27,
          "draws": 31,
          "evaluated_setting_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": 54,
          "raw_elo_rating": 1470.7197466096768,
          "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": 34.804158602993404,
          "uncertainty": 23.66998624632421,
          "unilateral_faults": 0,
          "wins": 11
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 58,
          "capped_draws": 4,
          "coverage_status": "rated",
          "distinct_rated_opponents": 29,
          "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": 20,
          "model": "z-ai/glm-5.2",
          "point_rating_method": "sequential_elo",
          "public_id": "E-583be34ca1fb2631",
          "rated_matches": 58,
          "raw_elo_rating": 1513.2067256039966,
          "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": 41.56883825039476,
          "uncertainty": 21.344455490411935,
          "unilateral_faults": 0,
          "wins": 12
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 34,
          "capped_draws": 3,
          "coverage_status": "under_covered",
          "distinct_rated_opponents": 17,
          "draws": 8,
          "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": 12,
          "model": "z-ai/glm-5.2",
          "point_rating_method": "sequential_elo",
          "public_id": "E-d047860be3ae0d90",
          "rated_matches": 34,
          "raw_elo_rating": 1508.7509672095766,
          "reasoning": "xhigh",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_7fad32_to_brackets_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "xhigh",
          "repair_status": "first_pass",
          "score": 38.519210099767925,
          "uncertainty": 40.76542547285167,
          "unilateral_faults": 0,
          "wins": 14
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 32,
          "capped_draws": 1,
          "coverage_status": "under_covered",
          "distinct_rated_opponents": 16,
          "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": "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": 6,
          "model": "z-ai/glm-5.2",
          "point_rating_method": "sequential_elo",
          "public_id": "E-d3a5bd501d8146e0",
          "rated_matches": 32,
          "raw_elo_rating": 1558.4052871388826,
          "reasoning": "xhigh",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_7fad32_to_brackets_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "xhigh",
          "repair_status": "first_pass",
          "score": 45.78546547495367,
          "uncertainty": 43.288827977848925,
          "unilateral_faults": 0,
          "wins": 13
        }
      ],
      "GB2-04": [
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 98,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 44,
          "draws": 17,
          "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": 98,
          "raw_elo_rating": 1865.823673582791,
          "reasoning": "xhigh",
          "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": 6.501890762960602,
          "unilateral_faults": 0,
          "wins": 76
        },
        {
          "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": 1582.9690692214492,
          "reasoning": "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": 47.83931957227835,
          "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": "legacy_shared_thinking_budget",
          "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": 76,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 38,
          "draws": 48,
          "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": 76,
          "raw_elo_rating": 1552.8865414749796,
          "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": 42.16676257859201,
          "uncertainty": 13.230288229818967,
          "unilateral_faults": 0,
          "wins": 14
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 104,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 52,
          "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": 1483.6856058732603,
          "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": 30.749828609175978,
          "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": "legacy_shared_thinking_budget",
          "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": 40,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 20,
          "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": 22,
          "model": "claude-opus-4-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-f40463f635c43598",
          "rated_matches": 40,
          "raw_elo_rating": 1337.681790240821,
          "reasoning": "high",
          "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": 0.0,
          "uncertainty": 34.33688094430304,
          "unilateral_faults": 0,
          "wins": 1
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 92,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 41,
          "draws": 35,
          "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": 92,
          "raw_elo_rating": 1623.201730875163,
          "reasoning": "xhigh",
          "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": 55.68784123456057,
          "uncertainty": 8.09758473652126,
          "unilateral_faults": 0,
          "wins": 40
        },
        {
          "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": 1490.9532680536443,
          "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": 31.313916897298004,
          "uncertainty": 10.482614454664043,
          "unilateral_faults": 0,
          "wins": 9
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 104,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 52,
          "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": 1481.537434054386,
          "reasoning": "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": 30.39355816481966,
          "uncertainty": 5.045003647426665,
          "unilateral_faults": 0,
          "wins": 5
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 98,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 49,
          "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-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-048d3dcf802043b4",
          "rated_matches": 98,
          "raw_elo_rating": 1557.8175182985399,
          "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": 44.040583390386246,
          "uncertainty": 6.501890762960602,
          "unilateral_faults": 0,
          "wins": 17
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 78,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 35,
          "draws": 10,
          "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": 78,
          "raw_elo_rating": 1694.3212314288232,
          "reasoning": "xhigh",
          "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": 67.96851702113216,
          "uncertainty": 12.5043950463012,
          "unilateral_faults": 0,
          "wins": 55
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 98,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 49,
          "draws": 54,
          "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": 98,
          "raw_elo_rating": 1504.8242989260918,
          "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": 34.41262761914292,
          "uncertainty": 6.501890762960602,
          "unilateral_faults": 0,
          "wins": 17
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 100,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 50,
          "draws": 25,
          "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": 100,
          "raw_elo_rating": 1600.0996631851501,
          "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": 51.79519895770521,
          "uncertainty": 6.001859510499461,
          "unilateral_faults": 0,
          "wins": 46
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 82,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 36,
          "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": 82,
          "raw_elo_rating": 1819.8717146747888,
          "reasoning": "xhigh",
          "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": 90.97833223839412,
          "uncertainty": 11.132129994845172,
          "unilateral_faults": 0,
          "wins": 61
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 100,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 50,
          "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-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": 100,
          "raw_elo_rating": 1567.7938393705367,
          "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": 45.925786860760766,
          "uncertainty": 6.001859510499461,
          "unilateral_faults": 0,
          "wins": 41
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 100,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 50,
          "draws": 70,
          "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": 100,
          "raw_elo_rating": 1488.2760299875736,
          "reasoning": "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": 31.478769660606087,
          "uncertainty": 6.001859510499461,
          "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": 1469.7658079724426,
          "reasoning": "enabled",
          "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": 26.333035635148633,
          "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": 1482.6080624665635,
          "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": 28.801808670018016,
          "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": 1376.1312280226116,
          "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": 9.943666245746922,
          "uncertainty": 13.985026918962571,
          "unilateral_faults": 0,
          "wins": 4
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 86,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 43,
          "draws": 52,
          "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": 86,
          "raw_elo_rating": 1465.1059463245633,
          "reasoning": "xhigh",
          "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": 26.709033756995762,
          "uncertainty": 9.855626741889738,
          "unilateral_faults": 0,
          "wins": 9
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 46,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 23,
          "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-3.1-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": 15,
          "model": "google/gemini-3.1-flash-lite",
          "point_rating_method": "sequential_elo",
          "public_id": "E-2be6f5c895691cb3",
          "rated_matches": 46,
          "raw_elo_rating": 1404.0919377589096,
          "reasoning": "high",
          "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": 12.814751118329694,
          "uncertainty": 29.182495748947275,
          "unilateral_faults": 0,
          "wins": 3
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 90,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 44,
          "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": "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": 4,
          "model": "google/gemini-3.1-flash-lite",
          "point_rating_method": "sequential_elo",
          "public_id": "E-860c31323fa5eda7",
          "rated_matches": 88,
          "raw_elo_rating": 1505.6208754393567,
          "reasoning": "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": 34.157939951088196,
          "uncertainty": 9.249894000318006,
          "unilateral_faults": 2,
          "wins": 8
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 98,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 49,
          "draws": 56,
          "evaluated_setting_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-32cfa6c9dfb1d16f",
          "rated_matches": 98,
          "raw_elo_rating": 1556.148668508276,
          "reasoning": "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": 43.737382109924624,
          "uncertainty": 6.501890762960602,
          "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": "low",
          "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": 46,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 23,
          "draws": 10,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "google/gemini-3.5-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": 25,
          "model": "google/gemini-3.5-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-8e95359e4cbd1851",
          "rated_matches": 46,
          "raw_elo_rating": 1415.7715836747748,
          "reasoning": "high",
          "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": 14.936741735872697,
          "uncertainty": 29.182495748947275,
          "unilateral_faults": 0,
          "wins": 11
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 40,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 20,
          "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": "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-39ebef34ae0ea1cb",
          "rated_matches": 40,
          "raw_elo_rating": 1409.207990249776,
          "reasoning": "high",
          "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": 12.995079338949578,
          "uncertainty": 34.33688094430304,
          "unilateral_faults": 0,
          "wins": 4
        },
        {
          "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": 1503.808618075588,
          "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": 34.665054859426824,
          "uncertainty": 3.4955591261534025,
          "unilateral_faults": 0,
          "wins": 10
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 51,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 26,
          "draws": 42,
          "evaluated_setting_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": 4,
          "model": "google/gemini-3.5-flash-lite",
          "point_rating_method": "sequential_elo",
          "public_id": "E-6098de52ddfabfb1",
          "rated_matches": 50,
          "raw_elo_rating": 1511.0193759194003,
          "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": 32.66581779874579,
          "uncertainty": 26.264004201400486,
          "unilateral_faults": 0,
          "wins": 4
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 20,
          "capped_draws": 0,
          "coverage_status": "under_covered",
          "distinct_rated_opponents": 10,
          "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": "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-6a79049fd9ab6f5d",
          "rated_matches": 20,
          "raw_elo_rating": 1526.6735769833929,
          "reasoning": "minimal",
          "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": 29.82761442249626,
          "uncertainty": 65.3589451179962,
          "unilateral_faults": 0,
          "wins": 4
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 42,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 21,
          "draws": 21,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "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": 11,
          "model": "google/gemini-3.5-flash-lite",
          "point_rating_method": "sequential_elo",
          "public_id": "E-953992515ec1424d",
          "rated_matches": 42,
          "raw_elo_rating": 1510.908533785498,
          "reasoning": "high",
          "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": 31.739405113778663,
          "uncertainty": 32.49928516630233,
          "unilateral_faults": 0,
          "wins": 10
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 18,
          "capped_draws": 0,
          "coverage_status": "under_covered",
          "distinct_rated_opponents": 9,
          "draws": 10,
          "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": 4,
          "model": "google/gemini-3.5-flash-lite",
          "point_rating_method": "sequential_elo",
          "public_id": "E-b05b0185d0e8dc2a",
          "rated_matches": 18,
          "raw_elo_rating": 1493.8451062756994,
          "reasoning": "minimal",
          "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": 23.049464206984855,
          "uncertainty": 70.95786693528086,
          "unilateral_faults": 0,
          "wins": 4
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 20,
          "capped_draws": 0,
          "coverage_status": "under_covered",
          "distinct_rated_opponents": 10,
          "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": "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": 1,
          "model": "google/gemini-3.6-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-0b528ba96380a3b5",
          "rated_matches": 20,
          "raw_elo_rating": 1500.744166605296,
          "reasoning": "minimal",
          "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": 25.11668688778358,
          "uncertainty": 65.3589451179962,
          "unilateral_faults": 0,
          "wins": 2
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 24,
          "capped_draws": 0,
          "coverage_status": "under_covered",
          "distinct_rated_opponents": 12,
          "draws": 19,
          "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": 4,
          "model": "google/gemini-3.6-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-846809faa1345207",
          "rated_matches": 24,
          "raw_elo_rating": 1470.2178477461143,
          "reasoning": "minimal",
          "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": 20.89453103634271,
          "uncertainty": 56.25,
          "unilateral_faults": 0,
          "wins": 1
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 38,
          "capped_draws": 0,
          "coverage_status": "under_covered",
          "distinct_rated_opponents": 19,
          "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
            "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": "google/gemini-3.6-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-a5a73c81dfcf4540",
          "rated_matches": 38,
          "raw_elo_rating": 1384.2675212009046,
          "reasoning": "high",
          "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": 8.176447443583427,
          "uncertainty": 36.31407690254356,
          "unilateral_faults": 0,
          "wins": 6
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 40,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 20,
          "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": "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-ccfb6c993d1622b0",
          "rated_matches": 40,
          "raw_elo_rating": 1579.4624729655434,
          "reasoning": "high",
          "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": 43.92738820515834,
          "uncertainty": 34.33688094430304,
          "unilateral_faults": 0,
          "wins": 19
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 63,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 32,
          "draws": 51,
          "evaluated_setting_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-cefb1dec9ce36375",
          "rated_matches": 63,
          "raw_elo_rating": 1465.1675896513302,
          "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": 25.42746967287035,
          "uncertainty": 18.75,
          "unilateral_faults": 0,
          "wins": 5
        },
        {
          "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": 1500.520993952449,
          "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": 34.272780519974965,
          "uncertainty": 2.084924851410568,
          "unilateral_faults": 0,
          "wins": 20
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 56,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 27,
          "draws": 44,
          "evaluated_setting_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": 4,
          "model": "google/gemma-4-31b-it",
          "point_rating_method": "sequential_elo",
          "public_id": "E-62ca2464f2212fc9",
          "rated_matches": 54,
          "raw_elo_rating": 1509.1633957360891,
          "reasoning": "enabled",
          "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": 32.70564887564202,
          "uncertainty": 23.66998624632421,
          "unilateral_faults": 2,
          "wins": 6
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 86,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 42,
          "draws": 67,
          "evaluated_setting_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": 86,
          "raw_elo_rating": 1491.3691141009099,
          "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": 31.480599265900732,
          "uncertainty": 9.855626741889738,
          "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": 1469.2709415655665,
          "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": 27.37461139902881,
          "uncertainty": 10.482614454664043,
          "unilateral_faults": 0,
          "wins": 4
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 96,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 48,
          "draws": 60,
          "evaluated_setting_identity": {
            "canonical_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-6f1aae863396df76",
          "rated_matches": 96,
          "raw_elo_rating": 1495.669383234101,
          "reasoning": "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": 32.67442303505885,
          "uncertainty": 7.017308256680951,
          "unilateral_faults": 0,
          "wins": 17
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 46,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 23,
          "draws": 27,
          "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": 15,
          "model": "gpt-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-7e3da77777a95e31",
          "rated_matches": 46,
          "raw_elo_rating": 1423.0741008790983,
          "reasoning": "high",
          "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": 16.26348341140345,
          "uncertainty": 29.182495748947275,
          "unilateral_faults": 0,
          "wins": 4
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 100,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 50,
          "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-5.4",
            "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": 13,
          "model": "gpt-5.4",
          "point_rating_method": "sequential_elo",
          "public_id": "E-0b4132559ee98caf",
          "rated_matches": 100,
          "raw_elo_rating": 1509.4148214952497,
          "reasoning": "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": 35.31932420897261,
          "uncertainty": 6.001859510499461,
          "unilateral_faults": 0,
          "wins": 22
        },
        {
          "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": "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": 88,
          "raw_elo_rating": 1489.5133398135404,
          "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": 31.231477991886752,
          "uncertainty": 9.249894000318006,
          "unilateral_faults": 0,
          "wins": 11
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 94,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 42,
          "draws": 34,
          "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": 94,
          "raw_elo_rating": 1635.5726584504935,
          "reasoning": "xhigh",
          "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": 58.01517252922639,
          "uncertainty": 7.54891760425771,
          "unilateral_faults": 0,
          "wins": 36
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 88,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 43,
          "draws": 57,
          "evaluated_setting_identity": {
            "canonical_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": 15,
          "model": "gpt-5.4-mini",
          "point_rating_method": "sequential_elo",
          "public_id": "E-0880cdf1a43cb90c",
          "rated_matches": 88,
          "raw_elo_rating": 1470.7557500321805,
          "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": 27.82354680882762,
          "uncertainty": 9.249894000318006,
          "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": 1561.7564985722227,
          "reasoning": "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": 44.441938728209706,
          "uncertainty": 8.664241836095918,
          "unilateral_faults": 0,
          "wins": 20
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 96,
          "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-5.4-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": 96,
          "raw_elo_rating": 1564.996519212638,
          "reasoning": "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": 45.26997029285312,
          "uncertainty": 7.017308256680951,
          "unilateral_faults": 0,
          "wins": 25
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 84,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 41,
          "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": 33,
          "model": "gpt-5.5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-64bf5daf186f8119",
          "rated_matches": 84,
          "raw_elo_rating": 1401.941773211182,
          "reasoning": "xhigh",
          "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": 15.142060466906322,
          "uncertainty": 10.482614454664043,
          "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": 1486.0440995567778,
          "reasoning": "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": 31.14381674077765,
          "uncertainty": 5.516463908214657,
          "unilateral_faults": 0,
          "wins": 22
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 94,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 46,
          "draws": 64,
          "evaluated_setting_identity": {
            "canonical_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": 94,
          "raw_elo_rating": 1490.875178692428,
          "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": 31.726131179809055,
          "uncertainty": 7.54891760425771,
          "unilateral_faults": 0,
          "wins": 12
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 96,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 48,
          "draws": 85,
          "evaluated_setting_identity": {
            "canonical_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": 96,
          "raw_elo_rating": 1508.170150760798,
          "reasoning": "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": 34.94559731506889,
          "uncertainty": 7.017308256680951,
          "unilateral_faults": 0,
          "wins": 6
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 86,
          "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-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": 86,
          "raw_elo_rating": 1483.0322829267293,
          "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": 29.965940546014295,
          "uncertainty": 9.855626741889738,
          "unilateral_faults": 0,
          "wins": 7
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 82,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 40,
          "draws": 42,
          "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": 24,
          "model": "gpt-5.6-luna",
          "point_rating_method": "sequential_elo",
          "public_id": "E-e348813cda8b38b7",
          "rated_matches": 82,
          "raw_elo_rating": 1492.3136234631593,
          "reasoning": "xhigh",
          "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": 31.466665424316382,
          "uncertainty": 11.132129994845172,
          "unilateral_faults": 0,
          "wins": 16
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 94,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 43,
          "draws": 42,
          "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": 94,
          "raw_elo_rating": 1656.1290756470048,
          "reasoning": "xhigh",
          "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": 61.74991968984401,
          "uncertainty": 7.54891760425771,
          "unilateral_faults": 0,
          "wins": 46
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 106,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 53,
          "draws": 85,
          "evaluated_setting_identity": {
            "canonical_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": 106,
          "raw_elo_rating": 1530.4112566798308,
          "reasoning": "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": 39.33968507396859,
          "uncertainty": 4.586824452283178,
          "unilateral_faults": 0,
          "wins": 15
        },
        {
          "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": 1509.0423085525442,
          "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": 34.50597954900976,
          "uncertainty": 11.132129994845172,
          "unilateral_faults": 0,
          "wins": 13
        },
        {
          "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-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": 86,
          "raw_elo_rating": 1523.1627836273447,
          "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": 37.25696174455382,
          "uncertainty": 9.855626741889738,
          "unilateral_faults": 0,
          "wins": 8
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 96,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 48,
          "draws": 74,
          "evaluated_setting_identity": {
            "canonical_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": 96,
          "raw_elo_rating": 1514.0428742199645,
          "reasoning": "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": 36.01257007858806,
          "uncertainty": 7.017308256680951,
          "unilateral_faults": 0,
          "wins": 13
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 90,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 43,
          "draws": 41,
          "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": 90,
          "raw_elo_rating": 1561.9585279553617,
          "reasoning": "xhigh",
          "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": 44.4786439895316,
          "uncertainty": 8.664241836095918,
          "unilateral_faults": 0,
          "wins": 31
        },
        {
          "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": 1429.7116213239594,
          "reasoning": "enabled",
          "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": 17.893598364366323,
          "uncertainty": 26.264004201400486,
          "unilateral_faults": 0,
          "wins": 4
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 114,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 47,
          "draws": 101,
          "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": 6,
          "model": "inclusionai/ling-3.0-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-f38039bb8cc277a1",
          "rated_matches": 114,
          "raw_elo_rating": 1496.113459457968,
          "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": 33.35713798385482,
          "uncertainty": 2.875240412015687,
          "unilateral_faults": 0,
          "wins": 7
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 24,
          "capped_draws": 0,
          "coverage_status": "under_covered",
          "distinct_rated_opponents": 12,
          "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": "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": 8,
          "model": "meituan/longcat-2.0",
          "point_rating_method": "sequential_elo",
          "public_id": "E-4ccf296e55b59be3",
          "rated_matches": 22,
          "raw_elo_rating": 1411.4338858377105,
          "reasoning": "enabled",
          "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": 9.59572803499691,
          "uncertainty": 60.5072070285374,
          "unilateral_faults": 2,
          "wins": 1
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 50,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 25,
          "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": "meituan/longcat-2.0",
            "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 13,
          "model": "meituan/longcat-2.0",
          "point_rating_method": "sequential_elo",
          "public_id": "E-9c9e87bb30b3cb99",
          "rated_matches": 50,
          "raw_elo_rating": 1412.4235384600008,
          "reasoning": "enabled",
          "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": 14.752651293120403,
          "uncertainty": 26.264004201400486,
          "unilateral_faults": 0,
          "wins": 2
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 98,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 49,
          "draws": 54,
          "evaluated_setting_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": 22,
          "model": "meituan/longcat-2.0",
          "point_rating_method": "sequential_elo",
          "public_id": "E-9e1d4bf411e97fa6",
          "rated_matches": 98,
          "raw_elo_rating": 1586.3561576652844,
          "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": 49.225562918867894,
          "uncertainty": 6.501890762960602,
          "unilateral_faults": 0,
          "wins": 22
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 64,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 32,
          "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": "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": 7,
          "model": "minimax/minimax-m3",
          "point_rating_method": "sequential_elo",
          "public_id": "E-c60620c3c72a6064",
          "rated_matches": 64,
          "raw_elo_rating": 1496.4810512769454,
          "reasoning": "enabled",
          "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": 31.186735485803233,
          "uncertainty": 18.26736729460423,
          "unilateral_faults": 0,
          "wins": 6
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 64,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 32,
          "draws": 52,
          "evaluated_setting_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": 7,
          "model": "moonshotai/kimi-k2.7-code",
          "point_rating_method": "sequential_elo",
          "public_id": "E-eb97811a38950c20",
          "rated_matches": 64,
          "raw_elo_rating": 1481.7071638258212,
          "reasoning": "enabled",
          "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": 28.50257444344345,
          "uncertainty": 18.26736729460423,
          "unilateral_faults": 0,
          "wins": 5
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 32,
          "capped_draws": 0,
          "coverage_status": "under_covered",
          "distinct_rated_opponents": 16,
          "draws": 17,
          "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": 4,
          "model": "moonshotai/kimi-k3",
          "point_rating_method": "sequential_elo",
          "public_id": "E-3c06949f23d4a77f",
          "rated_matches": 32,
          "raw_elo_rating": 1562.2866801608545,
          "reasoning": "low",
          "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": 39.50571055811572,
          "uncertainty": 43.288827977848925,
          "unilateral_faults": 0,
          "wins": 11
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 44,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 22,
          "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": "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": 9,
          "model": "moonshotai/kimi-k3",
          "point_rating_method": "sequential_elo",
          "public_id": "E-601725df2c678708",
          "rated_matches": 44,
          "raw_elo_rating": 1573.7970134206257,
          "reasoning": "max",
          "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": 43.41423713079391,
          "uncertainty": 30.785599249992988,
          "unilateral_faults": 0,
          "wins": 19
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 46,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 21,
          "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": "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": 5,
          "model": "moonshotai/kimi-k3",
          "point_rating_method": "sequential_elo",
          "public_id": "E-7c724729d138057b",
          "rated_matches": 42,
          "raw_elo_rating": 1534.645824597623,
          "reasoning": "high",
          "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": 36.0520622569886,
          "uncertainty": 32.49928516630233,
          "unilateral_faults": 0,
          "wins": 7
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 94,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 46,
          "draws": 81,
          "evaluated_setting_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": 94,
          "raw_elo_rating": 1475.0635006450743,
          "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": 28.853421449925953,
          "uncertainty": 7.54891760425771,
          "unilateral_faults": 0,
          "wins": 5
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 46,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 23,
          "draws": 27,
          "evaluated_setting_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": 15,
          "model": "nvidia/nemotron-3-ultra-550b-a55b",
          "point_rating_method": "sequential_elo",
          "public_id": "E-958dea26b779a042",
          "rated_matches": 46,
          "raw_elo_rating": 1416.7179169940546,
          "reasoning": "high",
          "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": 15.108674210456737,
          "uncertainty": 29.182495748947275,
          "unilateral_faults": 0,
          "wins": 4
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 60,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 30,
          "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": "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": 60,
          "raw_elo_rating": 1504.4747006526225,
          "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": 32.34819561268509,
          "uncertainty": 20.268439966447993,
          "unilateral_faults": 0,
          "wins": 7
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 88,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 44,
          "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": 1463.6610917058263,
          "reasoning": "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": 26.534569513484524,
          "uncertainty": 9.249894000318006,
          "unilateral_faults": 0,
          "wins": 9
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 46,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 23,
          "draws": 22,
          "evaluated_setting_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": 18,
          "model": "openai/gpt-oss-120b",
          "point_rating_method": "sequential_elo",
          "public_id": "E-3a27113d21c73b01",
          "rated_matches": 46,
          "raw_elo_rating": 1413.6729432495829,
          "reasoning": "high",
          "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": 14.555454895164242,
          "uncertainty": 29.182495748947275,
          "unilateral_faults": 0,
          "wins": 6
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 96,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 48,
          "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": 1465.1792260115858,
          "reasoning": "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": 27.134886304266157,
          "uncertainty": 7.017308256680951,
          "unilateral_faults": 0,
          "wins": 2
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 34,
          "capped_draws": 0,
          "coverage_status": "under_covered",
          "distinct_rated_opponents": 17,
          "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": "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": 14,
          "model": "openai/gpt-oss-120b",
          "point_rating_method": "sequential_elo",
          "public_id": "E-f6de1ce39e48807c",
          "rated_matches": 34,
          "raw_elo_rating": 1394.8462834549794,
          "reasoning": "low",
          "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": 9.451439719406691,
          "uncertainty": 40.76542547285167,
          "unilateral_faults": 0,
          "wins": 2
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 40,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 20,
          "draws": 27,
          "evaluated_setting_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": 9,
          "model": "poolside/laguna-s-2.1",
          "point_rating_method": "sequential_elo",
          "public_id": "E-e996fd38983e3b7f",
          "rated_matches": 40,
          "raw_elo_rating": 1488.1906395787857,
          "reasoning": "enabled",
          "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": 27.34486716917701,
          "uncertainty": 34.33688094430304,
          "unilateral_faults": 0,
          "wins": 4
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 64,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 32,
          "draws": 38,
          "evaluated_setting_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": 16,
          "model": "qwen/qwen3.7-max",
          "point_rating_method": "sequential_elo",
          "public_id": "E-ea08328e287de1ad",
          "rated_matches": 64,
          "raw_elo_rating": 1482.9185199612966,
          "reasoning": "enabled",
          "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": 28.722657001810248,
          "uncertainty": 18.26736729460423,
          "unilateral_faults": 0,
          "wins": 10
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 70,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 34,
          "draws": 57,
          "evaluated_setting_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": 70,
          "raw_elo_rating": 1474.1281441770377,
          "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": 27.51487556975524,
          "uncertainty": 15.58908290969266,
          "unilateral_faults": 0,
          "wins": 5
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 96,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 48,
          "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": "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": 96,
          "raw_elo_rating": 1524.4271477634718,
          "reasoning": "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": 37.89921383372028,
          "uncertainty": 7.017308256680951,
          "unilateral_faults": 0,
          "wins": 11
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 70,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 35,
          "draws": 42,
          "evaluated_setting_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": 70,
          "raw_elo_rating": 1509.5599956004069,
          "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": 33.952233073927275,
          "uncertainty": 15.58908290969266,
          "unilateral_faults": 0,
          "wins": 15
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 46,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 23,
          "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": 14,
          "model": "tencent/hy3-preview",
          "point_rating_method": "sequential_elo",
          "public_id": "E-51c104b34ef2a244",
          "rated_matches": 46,
          "raw_elo_rating": 1441.0086683971886,
          "reasoning": "high",
          "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": 19.521885616164113,
          "uncertainty": 29.182495748947275,
          "unilateral_faults": 0,
          "wins": 6
        },
        {
          "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": 1450.017819843153,
          "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": 23.96778089192692,
          "uncertainty": 9.855626741889738,
          "unilateral_faults": 0,
          "wins": 18
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 90,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 44,
          "draws": 75,
          "evaluated_setting_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": 90,
          "raw_elo_rating": 1496.175509699153,
          "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": 32.527001915886224,
          "uncertainty": 8.664241836095918,
          "unilateral_faults": 0,
          "wins": 4
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 44,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 22,
          "draws": 19,
          "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": 11,
          "model": "thinkingmachines/inkling",
          "point_rating_method": "sequential_elo",
          "public_id": "E-f130161523da1e6b",
          "rated_matches": 44,
          "raw_elo_rating": 1494.2033950634172,
          "reasoning": "max",
          "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": 28.95344674494225,
          "uncertainty": 30.785599249992988,
          "unilateral_faults": 0,
          "wins": 14
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 42,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 21,
          "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": 4,
          "model": "thinkingmachines/inkling",
          "point_rating_method": "sequential_elo",
          "public_id": "E-fce01db31ecf26d2",
          "rated_matches": 42,
          "raw_elo_rating": 1492.516457423049,
          "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": 28.397881427239696,
          "uncertainty": 32.49928516630233,
          "unilateral_faults": 0,
          "wins": 3
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 40,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 20,
          "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": "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-07caaa12175b0b3c",
          "rated_matches": 40,
          "raw_elo_rating": 1428.7678976898524,
          "reasoning": "high",
          "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": 16.548777830054647,
          "uncertainty": 34.33688094430304,
          "unilateral_faults": 0,
          "wins": 7
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 28,
          "capped_draws": 0,
          "coverage_status": "under_covered",
          "distinct_rated_opponents": 14,
          "draws": 22,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "low",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "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": 3,
          "model": "x-ai/grok-4.5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-5a4033db1131bf1d",
          "rated_matches": 28,
          "raw_elo_rating": 1486.528573612316,
          "reasoning": "low",
          "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": 24.897473493704123,
          "uncertainty": 49.09766908852594,
          "unilateral_faults": 0,
          "wins": 3
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 108,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 54,
          "draws": 80,
          "evaluated_setting_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": 108,
          "raw_elo_rating": 1488.922495957919,
          "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": 31.866644636143132,
          "uncertainty": 4.1413142610575715,
          "unilateral_faults": 0,
          "wins": 12
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 64,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 32,
          "draws": 56,
          "evaluated_setting_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": 5,
          "model": "x-ai/grok-build-0.1",
          "point_rating_method": "sequential_elo",
          "public_id": "E-85934b32572399da",
          "rated_matches": 64,
          "raw_elo_rating": 1474.1169273355108,
          "reasoning": "enabled",
          "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": 27.12355912625024,
          "uncertainty": 18.26736729460423,
          "unilateral_faults": 0,
          "wins": 3
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 54,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 27,
          "draws": 38,
          "evaluated_setting_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": 13,
          "model": "xiaomi/mimo-v2.5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-00e6914e513b1656",
          "rated_matches": 54,
          "raw_elo_rating": 1484.6753588209492,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "repaired",
          "score": 28.256594088339913,
          "uncertainty": 23.66998624632421,
          "unilateral_faults": 0,
          "wins": 3
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 54,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 27,
          "draws": 37,
          "evaluated_setting_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": 16,
          "model": "xiaomi/mimo-v2.5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-23e877112cb95491",
          "rated_matches": 54,
          "raw_elo_rating": 1439.2294400822045,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "repaired",
          "score": 19.999852928212512,
          "uncertainty": 23.66998624632421,
          "unilateral_faults": 0,
          "wins": 1
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 62,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 31,
          "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": "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": 9,
          "model": "xiaomi/mimo-v2.5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-2f7e15b8aa123825",
          "rated_matches": 62,
          "raw_elo_rating": 1466.7131243673532,
          "reasoning": "enabled",
          "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": 25.636454231351987,
          "uncertainty": 19.244078834871203,
          "unilateral_faults": 0,
          "wins": 3
        },
        {
          "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": 1509.679130642027,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "repaired",
          "score": 34.207021350202915,
          "uncertainty": 13.985026918962571,
          "unilateral_faults": 0,
          "wins": 18
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 66,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 33,
          "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": "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-d58c55e107783a21",
          "rated_matches": 66,
          "raw_elo_rating": 1474.7299039452644,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "repaired",
          "score": 27.370482875885422,
          "uncertainty": 17.33472217815261,
          "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": 1502.1064415265755,
          "reasoning": "high",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "repaired",
          "score": 32.47394764651104,
          "uncertainty": 16.4429265428846,
          "unilateral_faults": 0,
          "wins": 6
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 60,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 30,
          "draws": 36,
          "evaluated_setting_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": 9,
          "model": "xiaomi/mimo-v2.5-pro",
          "point_rating_method": "sequential_elo",
          "public_id": "E-ffdebde8a72ed049",
          "rated_matches": 60,
          "raw_elo_rating": 1558.4476161482546,
          "reasoning": "enabled",
          "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": 42.154145305697575,
          "uncertainty": 20.268439966447993,
          "unilateral_faults": 0,
          "wins": 15
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 68,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 34,
          "draws": 49,
          "evaluated_setting_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": 68,
          "raw_elo_rating": 1531.2317511480408,
          "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": 37.76551506173829,
          "uncertainty": 16.4429265428846,
          "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": 1501.1308285615892,
          "reasoning": "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": 32.1670764313632,
          "uncertainty": 17.33472217815261,
          "unilateral_faults": 0,
          "wins": 7
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 80,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 40,
          "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": "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": 80,
          "raw_elo_rating": 1472.1974048811812,
          "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": 27.714014908685787,
          "uncertainty": 11.805555555555554,
          "unilateral_faults": 0,
          "wins": 15
        }
      ],
      "GB2-05": [
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 98,
          "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-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": 98,
          "raw_elo_rating": 2007.5728572044336,
          "reasoning": "xhigh",
          "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": 90.25579059650316,
          "uncertainty": 6.501890762960602,
          "unilateral_faults": 0,
          "wins": 82
        },
        {
          "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": 1673.6388165109624,
          "reasoning": "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": 58.88434592732646,
          "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": "legacy_shared_thinking_budget",
          "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": 104,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 52,
          "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": 38,
          "model": "claude-opus-4-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-934b5bc34a7e20b9",
          "rated_matches": 104,
          "raw_elo_rating": 1592.219415390376,
          "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": 51.16554962876789,
          "uncertainty": 5.045003647426665,
          "unilateral_faults": 0,
          "wins": 66
        },
        {
          "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-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": 46,
          "model": "claude-opus-4-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-a75e9d71efa4a6bc",
          "rated_matches": 106,
          "raw_elo_rating": 1490.8078638278364,
          "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": 41.629120841132384,
          "uncertainty": 4.586824452283178,
          "unilateral_faults": 0,
          "wins": 60
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 54,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 27,
          "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": 26,
          "model": "claude-opus-4-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-ccacc93776fb7c88",
          "rated_matches": 54,
          "raw_elo_rating": 1464.860082832403,
          "reasoning": "high",
          "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": 37.739395426388306,
          "uncertainty": 23.66998624632421,
          "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": "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": "legacy_shared_thinking_budget",
          "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": 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": 54,
          "model": "claude-opus-4-8",
          "point_rating_method": "sequential_elo",
          "public_id": "E-233f9cae6335e53d",
          "rated_matches": 96,
          "raw_elo_rating": 1426.0141768671742,
          "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": 35.33051290926278,
          "uncertainty": 7.017308256680951,
          "unilateral_faults": 0,
          "wins": 42
        },
        {
          "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": "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": 63,
          "model": "claude-opus-4-8",
          "point_rating_method": "sequential_elo",
          "public_id": "E-6774d700e60de31a",
          "rated_matches": 116,
          "raw_elo_rating": 1532.5443530487862,
          "reasoning": "xhigh",
          "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": 45.72757509137996,
          "uncertainty": 2.4750163521024238,
          "unilateral_faults": 0,
          "wins": 53
        },
        {
          "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": "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": 55,
          "model": "claude-opus-4-8",
          "point_rating_method": "sequential_elo",
          "public_id": "E-924d7e6ee41b562e",
          "rated_matches": 120,
          "raw_elo_rating": 1542.2837822150532,
          "reasoning": "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": 46.70493564691155,
          "uncertainty": 1.7045454545454586,
          "unilateral_faults": 0,
          "wins": 65
        },
        {
          "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": "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": 116,
          "raw_elo_rating": 1985.5251096920047,
          "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": 88.47900640476404,
          "uncertainty": 2.4750163521024238,
          "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": "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": 112,
          "raw_elo_rating": 1876.0974674925728,
          "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": 78.09020662768593,
          "uncertainty": 3.286043419179858,
          "unilateral_faults": 0,
          "wins": 94
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 68,
          "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": 68,
          "raw_elo_rating": 2118.7722722673184,
          "reasoning": "xhigh",
          "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": 16.4429265428846,
          "unilateral_faults": 0,
          "wins": 68
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 68,
          "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": 68,
          "raw_elo_rating": 1805.196965973831,
          "reasoning": "xhigh",
          "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": 70.40538042295204,
          "uncertainty": 16.4429265428846,
          "unilateral_faults": 0,
          "wins": 46
        },
        {
          "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": 12,
          "model": "claude-opus-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-b53cb955b1d8baab",
          "rated_matches": 114,
          "raw_elo_rating": 1944.6811591254987,
          "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": 84.59401693770991,
          "uncertainty": 2.875240412015687,
          "unilateral_faults": 0,
          "wins": 102
        },
        {
          "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": "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": 110,
          "raw_elo_rating": 1960.9587096531482,
          "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": 86.06739228415002,
          "uncertainty": 3.707899787624953,
          "unilateral_faults": 0,
          "wins": 100
        },
        {
          "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-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": 1592.58297021455,
          "reasoning": "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": 51.19986121676889,
          "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": 1554.187571180924,
          "reasoning": "enabled",
          "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": 47.116586312570426,
          "uncertainty": 11.132129994845172,
          "unilateral_faults": 0,
          "wins": 46
        },
        {
          "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": 46,
          "model": "deepseek/deepseek-v4-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-06a41d0e11b18b77",
          "rated_matches": 76,
          "raw_elo_rating": 1376.1999302626996,
          "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": 30.160047415863634,
          "uncertainty": 13.230288229818967,
          "unilateral_faults": 0,
          "wins": 30
        },
        {
          "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": "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": 112,
          "raw_elo_rating": 1424.9492077155455,
          "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": 35.51172275800236,
          "uncertainty": 3.286043419179858,
          "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": "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-2c1cbd253f3a9d69",
          "rated_matches": 78,
          "raw_elo_rating": 1315.440789501957,
          "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": 24.48052611809984,
          "uncertainty": 12.5043950463012,
          "unilateral_faults": 0,
          "wins": 35
        },
        {
          "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": "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": 44,
          "model": "deepseek/deepseek-v4-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-b3d889b0631db85f",
          "rated_matches": 96,
          "raw_elo_rating": 1559.7911348935588,
          "reasoning": "xhigh",
          "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": 47.95611862982329,
          "uncertainty": 7.017308256680951,
          "unilateral_faults": 0,
          "wins": 52
        },
        {
          "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-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": 96,
          "raw_elo_rating": 1805.1338387843662,
          "reasoning": "xhigh",
          "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": 71.11107962938964,
          "uncertainty": 7.017308256680951,
          "unilateral_faults": 0,
          "wins": 61
        },
        {
          "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": "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": 96,
          "raw_elo_rating": 1431.2181246632692,
          "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": 35.82165124902767,
          "uncertainty": 7.017308256680951,
          "unilateral_faults": 0,
          "wins": 46
        },
        {
          "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": 1239.8542944594315,
          "reasoning": "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": 17.8000252646134,
          "uncertainty": 6.501890762960602,
          "unilateral_faults": 0,
          "wins": 28
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 46,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 23,
          "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": 42,
          "model": "google/gemini-3.1-flash-lite",
          "point_rating_method": "sequential_elo",
          "public_id": "E-a72dd193e1dc4331",
          "rated_matches": 46,
          "raw_elo_rating": 1209.6423317720237,
          "reasoning": "high",
          "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": 13.23623910301927,
          "uncertainty": 29.182495748947275,
          "unilateral_faults": 0,
          "wins": 4
        },
        {
          "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": "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": 57,
          "model": "google/gemini-3.1-flash-lite",
          "point_rating_method": "sequential_elo",
          "public_id": "E-d979b43c3aeea657",
          "rated_matches": 76,
          "raw_elo_rating": 1199.66391873774,
          "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": 13.498926473385124,
          "uncertainty": 13.230288229818967,
          "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": "low",
          "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": 1549.9264735902525,
          "reasoning": "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": 47.30683087113872,
          "uncertainty": 3.286043419179858,
          "unilateral_faults": 0,
          "wins": 58
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 50,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 25,
          "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": 26,
          "model": "google/gemini-3.5-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-b50da126631c1ea1",
          "rated_matches": 50,
          "raw_elo_rating": 1459.949544325857,
          "reasoning": "high",
          "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": 37.08009383434464,
          "uncertainty": 26.264004201400486,
          "unilateral_faults": 0,
          "wins": 24
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 34,
          "capped_draws": 0,
          "coverage_status": "under_covered",
          "distinct_rated_opponents": 17,
          "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": 27,
          "model": "google/gemini-3.5-flash-lite",
          "point_rating_method": "sequential_elo",
          "public_id": "E-06abb3c93d2072c8",
          "rated_matches": 34,
          "raw_elo_rating": 1254.9687139277914,
          "reasoning": "high",
          "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": 16.63951447666021,
          "uncertainty": 40.76542547285167,
          "unilateral_faults": 0,
          "wins": 7
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 24,
          "capped_draws": 0,
          "coverage_status": "under_covered",
          "distinct_rated_opponents": 11,
          "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": 16,
          "model": "google/gemini-3.5-flash-lite",
          "point_rating_method": "sequential_elo",
          "public_id": "E-214f636367cbdac4",
          "rated_matches": 22,
          "raw_elo_rating": 1353.8369912736307,
          "reasoning": "minimal",
          "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": 24.47995533731953,
          "uncertainty": 60.5072070285374,
          "unilateral_faults": 0,
          "wins": 6
        },
        {
          "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": "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": 56,
          "model": "google/gemini-3.5-flash-lite",
          "point_rating_method": "sequential_elo",
          "public_id": "E-3dd83d6fa9f8f758",
          "rated_matches": 74,
          "raw_elo_rating": 1260.8677419977996,
          "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": 19.218238123695905,
          "uncertainty": 13.985026918962571,
          "unilateral_faults": 0,
          "wins": 18
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 38,
          "capped_draws": 0,
          "coverage_status": "under_covered",
          "distinct_rated_opponents": 19,
          "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": 31,
          "model": "google/gemini-3.5-flash-lite",
          "point_rating_method": "sequential_elo",
          "public_id": "E-5b803013ec40d15d",
          "rated_matches": 38,
          "raw_elo_rating": 1237.5408240912482,
          "reasoning": "high",
          "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": 15.330792177830268,
          "uncertainty": 36.31407690254356,
          "unilateral_faults": 0,
          "wins": 7
        },
        {
          "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": "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": 54,
          "model": "google/gemini-3.5-flash-lite",
          "point_rating_method": "sequential_elo",
          "public_id": "E-8826ab29e7591ece",
          "rated_matches": 74,
          "raw_elo_rating": 1330.739735653201,
          "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": 25.812619217550747,
          "uncertainty": 13.985026918962571,
          "unilateral_faults": 0,
          "wins": 20
        },
        {
          "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": "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": 18,
          "model": "google/gemini-3.5-flash-lite",
          "point_rating_method": "sequential_elo",
          "public_id": "E-a870d09d3e1a40d4",
          "rated_matches": 22,
          "raw_elo_rating": 1296.1615294294538,
          "reasoning": "minimal",
          "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": 19.036658885234043,
          "uncertainty": 60.5072070285374,
          "unilateral_faults": 0,
          "wins": 4
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 72,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 36,
          "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": 3,
          "model": "google/gemini-3.6-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-5bcc61f900210bfa",
          "rated_matches": 72,
          "raw_elo_rating": 1944.9376572512983,
          "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": 83.72009823827334,
          "uncertainty": 14.770573598065289,
          "unilateral_faults": 0,
          "wins": 69
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 30,
          "capped_draws": 0,
          "coverage_status": "under_covered",
          "distinct_rated_opponents": 15,
          "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
            "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-8b9ff59d79afb558",
          "rated_matches": 30,
          "raw_elo_rating": 1665.3032357357797,
          "reasoning": "high",
          "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": 54.96687982792465,
          "uncertainty": 46.05265101338746,
          "unilateral_faults": 0,
          "wins": 23
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 20,
          "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": "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-9bef179ce22a6c93",
          "rated_matches": 20,
          "raw_elo_rating": 1586.7104366140052,
          "reasoning": "minimal",
          "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": 46.09177429753464,
          "uncertainty": 65.3589451179962,
          "unilateral_faults": 0,
          "wins": 13
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 32,
          "capped_draws": 0,
          "coverage_status": "under_covered",
          "distinct_rated_opponents": 16,
          "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
            "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-c4f143aad203feb3",
          "rated_matches": 32,
          "raw_elo_rating": 1577.226054226596,
          "reasoning": "high",
          "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": 46.863004311807074,
          "uncertainty": 43.288827977848925,
          "unilateral_faults": 0,
          "wins": 18
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 72,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 36,
          "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": 36,
          "model": "google/gemini-3.6-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-d95a1da824d70f6d",
          "rated_matches": 72,
          "raw_elo_rating": 1652.07513525259,
          "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": 56.0803104329967,
          "uncertainty": 14.770573598065289,
          "unilateral_faults": 0,
          "wins": 36
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 40,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 20,
          "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": 11,
          "model": "google/gemini-3.6-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-e23af86eb5787555",
          "rated_matches": 40,
          "raw_elo_rating": 1691.6033408260928,
          "reasoning": "minimal",
          "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": 58.33360096442092,
          "uncertainty": 34.33688094430304,
          "unilateral_faults": 0,
          "wins": 29
        },
        {
          "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": 1206.244527485814,
          "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": 14.548948613994082,
          "uncertainty": 7.54891760425771,
          "unilateral_faults": 0,
          "wins": 27
        },
        {
          "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": "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": 33,
          "model": "google/gemma-4-31b-it",
          "point_rating_method": "sequential_elo",
          "public_id": "E-fd1bc1e2e6ac48fb",
          "rated_matches": 78,
          "raw_elo_rating": 1535.4737363387264,
          "reasoning": "enabled",
          "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": 45.246802114196214,
          "uncertainty": 12.5043950463012,
          "unilateral_faults": 0,
          "wins": 45
        },
        {
          "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-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": 64,
          "model": "gpt-4.1",
          "point_rating_method": "sequential_elo",
          "public_id": "E-1b9f1f7b70f02927",
          "rated_matches": 92,
          "raw_elo_rating": 1184.8550619458447,
          "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": 12.488827301220297,
          "uncertainty": 8.09758473652126,
          "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": 1602.5266986191143,
          "reasoning": "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": 52.1027343192657,
          "uncertainty": 5.516463908214657,
          "unilateral_faults": 0,
          "wins": 50
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 48,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 24,
          "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": 21,
          "model": "gpt-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-c5ad048b6fb4e93d",
          "rated_matches": 48,
          "raw_elo_rating": 1609.7603755655746,
          "reasoning": "high",
          "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": 51.11214166332489,
          "uncertainty": 27.678571428571434,
          "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": "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": "low",
          "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": 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",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_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": 90,
          "raw_elo_rating": 1777.5579433554326,
          "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": 68.38417347397768,
          "uncertainty": 8.664241836095918,
          "unilateral_faults": 0,
          "wins": 65
        },
        {
          "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": "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": 68,
          "model": "gpt-5.4",
          "point_rating_method": "sequential_elo",
          "public_id": "E-cafab3c275850d3b",
          "rated_matches": 118,
          "raw_elo_rating": 1475.0224962569089,
          "reasoning": "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": 40.32822843528254,
          "uncertainty": 2.084924851410568,
          "unilateral_faults": 0,
          "wins": 50
        },
        {
          "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-5.4",
            "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": 92,
          "raw_elo_rating": 2032.5608459804337,
          "reasoning": "xhigh",
          "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": 92.49362898125582,
          "uncertainty": 8.09758473652126,
          "unilateral_faults": 0,
          "wins": 84
        },
        {
          "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-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-0791f6b66243ec1a",
          "rated_matches": 120,
          "raw_elo_rating": 1568.875101313137,
          "reasoning": "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": 49.214571951063434,
          "uncertainty": 1.7045454545454586,
          "unilateral_faults": 0,
          "wins": 72
        },
        {
          "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-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": 64,
          "model": "gpt-5.4-mini",
          "point_rating_method": "sequential_elo",
          "public_id": "E-427bdffeacc6c394",
          "rated_matches": 92,
          "raw_elo_rating": 1348.5279664398565,
          "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": 27.935953546031328,
          "uncertainty": 8.09758473652126,
          "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": 1261.571795536862,
          "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": 19.642199321792404,
          "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": 1211.7757764699222,
          "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": 14.986767312208398,
          "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": 1805.1714752058563,
          "reasoning": "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": 71.03306818811886,
          "uncertainty": 8.09758473652126,
          "unilateral_faults": 0,
          "wins": 75
        },
        {
          "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": "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": 77,
          "model": "gpt-5.4-nano",
          "point_rating_method": "sequential_elo",
          "public_id": "E-a0d8c8fd6b01598c",
          "rated_matches": 114,
          "raw_elo_rating": 1292.1590187874883,
          "reasoning": "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": 23.010262983466863,
          "uncertainty": 2.875240412015687,
          "unilateral_faults": 0,
          "wins": 37
        },
        {
          "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-5.5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_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-5.5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-6f42dbbf02274b56",
          "rated_matches": 90,
          "raw_elo_rating": 1553.2854909074172,
          "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": 47.21778129130201,
          "uncertainty": 8.664241836095918,
          "unilateral_faults": 0,
          "wins": 52
        },
        {
          "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": "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": 20,
          "model": "gpt-5.5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-762e9d80a60b41ed",
          "rated_matches": 96,
          "raw_elo_rating": 1913.7523653539108,
          "reasoning": "xhigh",
          "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": 81.36228215819001,
          "uncertainty": 7.017308256680951,
          "unilateral_faults": 0,
          "wins": 76
        },
        {
          "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": "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": 30,
          "model": "gpt-5.5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-ffa82d1e96e897ab",
          "rated_matches": 96,
          "raw_elo_rating": 1733.9891021907006,
          "reasoning": "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": 64.39657956468047,
          "uncertainty": 7.017308256680951,
          "unilateral_faults": 0,
          "wins": 66
        },
        {
          "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": "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": 56,
          "model": "gpt-5.6-luna",
          "point_rating_method": "sequential_elo",
          "public_id": "E-25a83ddaeb1268a4",
          "rated_matches": 106,
          "raw_elo_rating": 1618.20016176997,
          "reasoning": "xhigh",
          "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": 53.65215492250481,
          "uncertainty": 4.586824452283178,
          "unilateral_faults": 0,
          "wins": 50
        },
        {
          "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": 1059.7162217483137,
          "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": 0.5457336893360095,
          "uncertainty": 9.855626741889738,
          "unilateral_faults": 2,
          "wins": 7
        },
        {
          "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": 1599.0265614912312,
          "reasoning": "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": 52.00203493565957,
          "uncertainty": 2.4750163521024238,
          "unilateral_faults": 0,
          "wins": 57
        },
        {
          "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": 1662.6720777987493,
          "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": 57.70473458705692,
          "uncertainty": 6.501890762960602,
          "unilateral_faults": 0,
          "wins": 59
        },
        {
          "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-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": 33,
          "model": "gpt-5.6-sol",
          "point_rating_method": "sequential_elo",
          "public_id": "E-af9c2c2998294ad0",
          "rated_matches": 92,
          "raw_elo_rating": 1729.2371283141379,
          "reasoning": "xhigh",
          "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": 63.86653414034944,
          "uncertainty": 8.09758473652126,
          "unilateral_faults": 0,
          "wins": 59
        },
        {
          "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": 1672.1305254535307,
          "reasoning": "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": 58.59740424093167,
          "uncertainty": 6.501890762960602,
          "unilateral_faults": 0,
          "wins": 61
        },
        {
          "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": "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": 94,
          "raw_elo_rating": 1649.9512272105483,
          "reasoning": "xhigh",
          "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": 56.425112707893895,
          "uncertainty": 7.54891760425771,
          "unilateral_faults": 0,
          "wins": 52
        },
        {
          "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-5.6-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": 35,
          "model": "gpt-5.6-terra",
          "point_rating_method": "sequential_elo",
          "public_id": "E-1f00b423eab1c19d",
          "rated_matches": 88,
          "raw_elo_rating": 1578.1507673596157,
          "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": 49.52029893343254,
          "uncertainty": 9.249894000318006,
          "unilateral_faults": 0,
          "wins": 53
        },
        {
          "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": "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": 44,
          "model": "gpt-5.6-terra",
          "point_rating_method": "sequential_elo",
          "public_id": "E-9664e98d37ece097",
          "rated_matches": 108,
          "raw_elo_rating": 1604.4100113362138,
          "reasoning": "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": 52.384304794269354,
          "uncertainty": 4.1413142610575715,
          "unilateral_faults": 0,
          "wins": 64
        },
        {
          "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": "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": 69,
          "model": "meituan/longcat-2.0",
          "point_rating_method": "sequential_elo",
          "public_id": "E-067ab716d64e3e9a",
          "rated_matches": 90,
          "raw_elo_rating": 1171.0008029797596,
          "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": 11.1385056522926,
          "uncertainty": 8.664241836095918,
          "unilateral_faults": 2,
          "wins": 21
        },
        {
          "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": "openrouter",
            "effective_request_value": "enabled",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "meituan/longcat-2.0",
            "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 22,
          "model": "meituan/longcat-2.0",
          "point_rating_method": "sequential_elo",
          "public_id": "E-73a7ad076eeaa6ae",
          "rated_matches": 52,
          "raw_elo_rating": 1516.8265772811042,
          "reasoning": "enabled",
          "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": 42.548735401808244,
          "uncertainty": 24.930281974344517,
          "unilateral_faults": 0,
          "wins": 30
        },
        {
          "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": "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-8b7eb63d4f53d846",
          "rated_matches": 52,
          "raw_elo_rating": 1280.9325986704027,
          "reasoning": "enabled",
          "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": 20.285526477550572,
          "uncertainty": 24.930281974344517,
          "unilateral_faults": 0,
          "wins": 13
        },
        {
          "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": "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": 57,
          "model": "meituan/longcat-2.0",
          "point_rating_method": "sequential_elo",
          "public_id": "E-8cc657b7db4428cb",
          "rated_matches": 84,
          "raw_elo_rating": 1225.2854224221107,
          "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": 16.124489539369485,
          "uncertainty": 10.482614454664043,
          "unilateral_faults": 2,
          "wins": 27
        },
        {
          "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": "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": 112,
          "raw_elo_rating": 1469.2367408862915,
          "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": 39.69149287984802,
          "uncertainty": 3.286043419179858,
          "unilateral_faults": 0,
          "wins": 54
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 68,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 34,
          "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": 66,
          "model": "minimax/minimax-m3",
          "point_rating_method": "sequential_elo",
          "public_id": "E-fb8ac45946e32e22",
          "rated_matches": 68,
          "raw_elo_rating": 1108.414675586985,
          "reasoning": "enabled",
          "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": 4.644440711956799,
          "uncertainty": 16.4429265428846,
          "unilateral_faults": 0,
          "wins": 2
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 48,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 24,
          "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": 40,
          "model": "mistralai/mistral-medium-3-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-1954b83d439b455c",
          "rated_matches": 48,
          "raw_elo_rating": 1252.6537658690042,
          "reasoning": "high",
          "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": 17.40912343991944,
          "uncertainty": 27.678571428571434,
          "unilateral_faults": 0,
          "wins": 8
        },
        {
          "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": "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": 96,
          "raw_elo_rating": 1391.2176833271508,
          "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": 32.0464884077659,
          "uncertainty": 7.017308256680951,
          "unilateral_faults": 0,
          "wins": 44
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 64,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 32,
          "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": 24,
          "model": "moonshotai/kimi-k2.7-code",
          "point_rating_method": "sequential_elo",
          "public_id": "E-952fba19b28982d5",
          "rated_matches": 64,
          "raw_elo_rating": 1670.0314312667674,
          "reasoning": "enabled",
          "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": 57.51097387236131,
          "uncertainty": 18.26736729460423,
          "unilateral_faults": 0,
          "wins": 40
        },
        {
          "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": "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": 12,
          "model": "moonshotai/kimi-k3",
          "point_rating_method": "sequential_elo",
          "public_id": "E-4419230379dcd41e",
          "rated_matches": 52,
          "raw_elo_rating": 1712.1885468405728,
          "reasoning": "low",
          "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": 60.98661317118852,
          "uncertainty": 24.930281974344517,
          "unilateral_faults": 0,
          "wins": 40
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 56,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 28,
          "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": 21,
          "model": "moonshotai/kimi-k3",
          "point_rating_method": "sequential_elo",
          "public_id": "E-895556dde47644ae",
          "rated_matches": 56,
          "raw_elo_rating": 1581.175060687989,
          "reasoning": "high",
          "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": 48.807076069542,
          "uncertainty": 22.47661785325219,
          "unilateral_faults": 0,
          "wins": 35
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 66,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 33,
          "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": 56,
          "model": "nex-agi/nex-n2-pro",
          "point_rating_method": "sequential_elo",
          "public_id": "E-5f76f577111bee8d",
          "rated_matches": 66,
          "raw_elo_rating": 1177.8086480503327,
          "reasoning": "enabled",
          "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": 11.12637437556477,
          "uncertainty": 17.33472217815261,
          "unilateral_faults": 0,
          "wins": 10
        },
        {
          "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": "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": 52,
          "model": "nex-agi/nex-n2-pro",
          "point_rating_method": "sequential_elo",
          "public_id": "E-962a9da8812a74d4",
          "rated_matches": 104,
          "raw_elo_rating": 1500.9159982859114,
          "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": 42.54851301568021,
          "uncertainty": 5.045003647426665,
          "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": "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": 86,
          "raw_elo_rating": 1597.6892957530818,
          "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": 51.31857245670056,
          "uncertainty": 9.855626741889738,
          "unilateral_faults": 0,
          "wins": 53
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 50,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 25,
          "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": 36,
          "model": "nvidia/nemotron-3-ultra-550b-a55b",
          "point_rating_method": "sequential_elo",
          "public_id": "E-48ed5c5e00ef38fb",
          "rated_matches": 50,
          "raw_elo_rating": 1365.1921728533348,
          "reasoning": "high",
          "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": 28.137079813254427,
          "uncertainty": 26.264004201400486,
          "unilateral_faults": 0,
          "wins": 14
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 50,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 25,
          "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": 31,
          "model": "nvidia/nemotron-3-ultra-550b-a55b",
          "point_rating_method": "sequential_elo",
          "public_id": "E-da3b98638ff53ea9",
          "rated_matches": 50,
          "raw_elo_rating": 1410.0340038022753,
          "reasoning": "high",
          "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": 32.36916346728466,
          "uncertainty": 26.264004201400486,
          "unilateral_faults": 0,
          "wins": 19
        },
        {
          "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": "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": 48,
          "model": "o3",
          "point_rating_method": "sequential_elo",
          "public_id": "E-343b92f3dda3dcb5",
          "rated_matches": 112,
          "raw_elo_rating": 1546.9217609319278,
          "reasoning": "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": 47.02325201056916,
          "uncertainty": 3.286043419179858,
          "unilateral_faults": 0,
          "wins": 64
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 58,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 29,
          "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 28,
          "model": "o3",
          "point_rating_method": "sequential_elo",
          "public_id": "E-4724b57e861c4ecf",
          "rated_matches": 58,
          "raw_elo_rating": 1481.4182498230907,
          "reasoning": "high",
          "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": 39.47770581139428,
          "uncertainty": 21.344455490411935,
          "unilateral_faults": 0,
          "wins": 30
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 54,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 27,
          "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-03T16:00:00Z",
          "losses": 31,
          "model": "o3",
          "point_rating_method": "sequential_elo",
          "public_id": "E-61d05a26a332d2e5",
          "rated_matches": 54,
          "raw_elo_rating": 1477.2336049189955,
          "reasoning": "high",
          "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": 38.90718406162663,
          "uncertainty": 23.66998624632421,
          "unilateral_faults": 0,
          "wins": 23
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 32,
          "capped_draws": 0,
          "coverage_status": "under_covered",
          "distinct_rated_opponents": 16,
          "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-03T15:45:00Z",
          "losses": 17,
          "model": "o3",
          "point_rating_method": "sequential_elo",
          "public_id": "E-9bfe5e29476019eb",
          "rated_matches": 32,
          "raw_elo_rating": 1440.366983423129,
          "reasoning": "high",
          "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": 33.94651485996851,
          "uncertainty": 43.288827977848925,
          "unilateral_faults": 0,
          "wins": 15
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 34,
          "capped_draws": 0,
          "coverage_status": "under_covered",
          "distinct_rated_opponents": 17,
          "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-03T15:50:00Z",
          "losses": 17,
          "model": "o3",
          "point_rating_method": "sequential_elo",
          "public_id": "E-ffb183b7ecfe85e0",
          "rated_matches": 34,
          "raw_elo_rating": 1447.7539890513212,
          "reasoning": "high",
          "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": 34.83420890198426,
          "uncertainty": 40.76542547285167,
          "unilateral_faults": 0,
          "wins": 17
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 56,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 28,
          "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": 35,
          "model": "openai/gpt-oss-120b",
          "point_rating_method": "sequential_elo",
          "public_id": "E-172336d3fd38632a",
          "rated_matches": 56,
          "raw_elo_rating": 1401.6386697045618,
          "reasoning": "low",
          "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": 31.862785225358834,
          "uncertainty": 22.47661785325219,
          "unilateral_faults": 0,
          "wins": 21
        },
        {
          "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": "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": 114,
          "raw_elo_rating": 1455.3098804014994,
          "reasoning": "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": 38.408119849833696,
          "uncertainty": 2.875240412015687,
          "unilateral_faults": 0,
          "wins": 47
        },
        {
          "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": "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": 100,
          "raw_elo_rating": 1810.8806685198024,
          "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": 71.7301229385181,
          "uncertainty": 6.001859510499461,
          "unilateral_faults": 0,
          "wins": 76
        },
        {
          "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": "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": 46,
          "model": "poolside/laguna-s-2.1",
          "point_rating_method": "sequential_elo",
          "public_id": "E-21623e96b2b104e9",
          "rated_matches": 92,
          "raw_elo_rating": 1407.0390256107005,
          "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": 33.458112027447555,
          "uncertainty": 8.09758473652126,
          "unilateral_faults": 0,
          "wins": 46
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 50,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 25,
          "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": 40,
          "model": "poolside/laguna-s-2.1",
          "point_rating_method": "sequential_elo",
          "public_id": "E-53ce0020411c86d4",
          "rated_matches": 50,
          "raw_elo_rating": 1267.1393490091898,
          "reasoning": "enabled",
          "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": 18.883047490292018,
          "uncertainty": 26.264004201400486,
          "unilateral_faults": 0,
          "wins": 10
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 58,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 29,
          "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": 36,
          "model": "poolside/laguna-s-2.1",
          "point_rating_method": "sequential_elo",
          "public_id": "E-62e15a037ee860c1",
          "rated_matches": 58,
          "raw_elo_rating": 1394.0878683267222,
          "reasoning": "enabled",
          "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": 31.235636471008934,
          "uncertainty": 21.344455490411935,
          "unilateral_faults": 0,
          "wins": 22
        },
        {
          "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": "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": 41,
          "model": "qwen/qwen3.7-max",
          "point_rating_method": "sequential_elo",
          "public_id": "E-435ec29661cdc285",
          "rated_matches": 82,
          "raw_elo_rating": 1569.2962092388195,
          "reasoning": "enabled",
          "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": 48.54250980423797,
          "uncertainty": 11.132129994845172,
          "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": "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": 52,
          "model": "qwen/qwen3.7-max",
          "point_rating_method": "sequential_elo",
          "public_id": "E-c577c41440c17864",
          "rated_matches": 104,
          "raw_elo_rating": 1525.3995628419666,
          "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": 44.85922359902054,
          "uncertainty": 5.045003647426665,
          "unilateral_faults": 0,
          "wins": 52
        },
        {
          "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": "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": 43,
          "model": "qwen/qwen3.7-plus",
          "point_rating_method": "sequential_elo",
          "public_id": "E-6cc7454f585005c4",
          "rated_matches": 80,
          "raw_elo_rating": 1558.141803831932,
          "reasoning": "enabled",
          "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": 47.43893373716316,
          "uncertainty": 11.805555555555554,
          "unilateral_faults": 0,
          "wins": 37
        },
        {
          "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": "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": 52,
          "model": "qwen/qwen3.7-plus",
          "point_rating_method": "sequential_elo",
          "public_id": "E-94daaf1196d89c6c",
          "rated_matches": 100,
          "raw_elo_rating": 1504.6944028280163,
          "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": 42.83286645498502,
          "uncertainty": 6.001859510499461,
          "unilateral_faults": 0,
          "wins": 48
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 50,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 25,
          "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": 27,
          "model": "stepfun/step-3.7-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-358338a9fbdbcb6a",
          "rated_matches": 50,
          "raw_elo_rating": 1483.1982568705898,
          "reasoning": "high",
          "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": 39.274261517859706,
          "uncertainty": 26.264004201400486,
          "unilateral_faults": 0,
          "wins": 23
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 30,
          "capped_draws": 0,
          "coverage_status": "under_covered",
          "distinct_rated_opponents": 13,
          "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": 15,
          "model": "stepfun/step-3.7-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-50f22f1c15a8fd4a",
          "rated_matches": 26,
          "raw_elo_rating": 1435.5757190524112,
          "reasoning": "low",
          "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": 32.800743128476654,
          "uncertainty": 52.475044864937615,
          "unilateral_faults": 0,
          "wins": 11
        },
        {
          "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": "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-7b9b33921ba865f5",
          "rated_matches": 116,
          "raw_elo_rating": 1490.9069818743108,
          "reasoning": "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": 41.79792203718302,
          "uncertainty": 2.4750163521024238,
          "unilateral_faults": 0,
          "wins": 52
        },
        {
          "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": "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": 102,
          "raw_elo_rating": 1379.0311903903728,
          "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": 31.009668601208,
          "uncertainty": 5.516463908214657,
          "unilateral_faults": 0,
          "wins": 39
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 48,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 24,
          "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": 25,
          "model": "tencent/hy3-preview",
          "point_rating_method": "sequential_elo",
          "public_id": "E-92dc0ac61d798488",
          "rated_matches": 48,
          "raw_elo_rating": 1472.1934264239376,
          "reasoning": "high",
          "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": 38.12884404864786,
          "uncertainty": 27.678571428571434,
          "unilateral_faults": 0,
          "wins": 23
        },
        {
          "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": "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": 68,
          "model": "thinkingmachines/inkling",
          "point_rating_method": "sequential_elo",
          "public_id": "E-0f05573125dedc2b",
          "rated_matches": 102,
          "raw_elo_rating": 1350.745875849399,
          "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": 28.340156344800302,
          "uncertainty": 5.516463908214657,
          "unilateral_faults": 0,
          "wins": 34
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 34,
          "capped_draws": 0,
          "coverage_status": "under_covered",
          "distinct_rated_opponents": 17,
          "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": 30,
          "model": "thinkingmachines/inkling",
          "point_rating_method": "sequential_elo",
          "public_id": "E-2c483dc32fc18ba8",
          "rated_matches": 34,
          "raw_elo_rating": 1189.998924181859,
          "reasoning": "max",
          "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": 10.50779372907021,
          "uncertainty": 40.76542547285167,
          "unilateral_faults": 0,
          "wins": 4
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 122,
          "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": 78,
          "model": "thinkingmachines/inkling",
          "point_rating_method": "sequential_elo",
          "public_id": "E-ae60ed096a69eeff",
          "rated_matches": 122,
          "raw_elo_rating": 1331.9093913458112,
          "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": 26.878231343301803,
          "uncertainty": 1.3334817333716131,
          "unilateral_faults": 0,
          "wins": 44
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 36,
          "capped_draws": 0,
          "coverage_status": "under_covered",
          "distinct_rated_opponents": 18,
          "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": 27,
          "model": "thinkingmachines/inkling",
          "point_rating_method": "sequential_elo",
          "public_id": "E-e9202aa1565d1c4e",
          "rated_matches": 36,
          "raw_elo_rating": 1291.2455175290106,
          "reasoning": "max",
          "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": 20.238106190832827,
          "uncertainty": 38.449493652678655,
          "unilateral_faults": 0,
          "wins": 9
        },
        {
          "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": "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": 71,
          "model": "thinkingmachines/inkling",
          "point_rating_method": "sequential_elo",
          "public_id": "E-f7a1d86c7e241f8d",
          "rated_matches": 108,
          "raw_elo_rating": 1358.0512100543676,
          "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": 29.133446524932413,
          "uncertainty": 4.1413142610575715,
          "unilateral_faults": 0,
          "wins": 37
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 48,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 24,
          "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": 18,
          "model": "x-ai/grok-4.5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-3c5879def34f7d38",
          "rated_matches": 48,
          "raw_elo_rating": 1611.4942172905676,
          "reasoning": "low",
          "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": 51.27577822917729,
          "uncertainty": 27.678571428571434,
          "unilateral_faults": 0,
          "wins": 30
        },
        {
          "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": 1662.7933410041032,
          "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": 58.02021794771947,
          "uncertainty": 2.4750163521024238,
          "unilateral_faults": 0,
          "wins": 70
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 34,
          "capped_draws": 0,
          "coverage_status": "under_covered",
          "distinct_rated_opponents": 17,
          "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": 18,
          "model": "x-ai/grok-4.5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-8e6cb252293b2af9",
          "rated_matches": 34,
          "raw_elo_rating": 1577.57790394916,
          "reasoning": "high",
          "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": 47.08673420067161,
          "uncertainty": 40.76542547285167,
          "unilateral_faults": 0,
          "wins": 16
        },
        {
          "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": "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": 30,
          "model": "x-ai/grok-build-0.1",
          "point_rating_method": "sequential_elo",
          "public_id": "E-4aac1b6621aeae38",
          "rated_matches": 74,
          "raw_elo_rating": 1582.6074425749334,
          "reasoning": "enabled",
          "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": 49.58339714709747,
          "uncertainty": 13.985026918962571,
          "unilateral_faults": 0,
          "wins": 44
        },
        {
          "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": 1644.3935809032257,
          "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": 55.72643086868543,
          "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": 1344.3523439503517,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "repaired",
          "score": 27.409130090108036,
          "uncertainty": 9.855626741889738,
          "unilateral_faults": 0,
          "wins": 32
        },
        {
          "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": "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": 48,
          "model": "xiaomi/mimo-v2.5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-ad48cf51fe7da3cc",
          "rated_matches": 70,
          "raw_elo_rating": 1309.2771310691762,
          "reasoning": "enabled",
          "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": 23.66591076906232,
          "uncertainty": 15.58908290969266,
          "unilateral_faults": 0,
          "wins": 22
        },
        {
          "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": 43,
          "model": "xiaomi/mimo-v2.5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-be8fc9653466bbe1",
          "rated_matches": 82,
          "raw_elo_rating": 1426.0236645885172,
          "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": 35.02072932706977,
          "uncertainty": 11.132129994845172,
          "unilateral_faults": 0,
          "wins": 39
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 58,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 29,
          "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": 48,
          "model": "xiaomi/mimo-v2.5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-faaa866ee28d6401",
          "rated_matches": 58,
          "raw_elo_rating": 1251.5086316908314,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "repaired",
          "score": 17.77928903823047,
          "uncertainty": 21.344455490411935,
          "unilateral_faults": 0,
          "wins": 10
        },
        {
          "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": "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": 52,
          "model": "xiaomi/mimo-v2.5-pro",
          "point_rating_method": "sequential_elo",
          "public_id": "E-9c228ad72a159b33",
          "rated_matches": 70,
          "raw_elo_rating": 1340.5127394994104,
          "reasoning": "enabled",
          "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": 26.613865949835468,
          "uncertainty": 15.58908290969266,
          "unilateral_faults": 0,
          "wins": 18
        },
        {
          "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": "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": 96,
          "raw_elo_rating": 1450.2800289578179,
          "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": 37.62067621907194,
          "uncertainty": 7.017308256680951,
          "unilateral_faults": 0,
          "wins": 50
        },
        {
          "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": "2026-07-11T14:00:45Z",
          "losses": 40,
          "model": "z-ai/glm-5.2",
          "point_rating_method": "sequential_elo",
          "public_id": "E-38e323f4ce233fa1",
          "rated_matches": 82,
          "raw_elo_rating": 1431.1307416928755,
          "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": 35.50272520181086,
          "uncertainty": 11.132129994845172,
          "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": "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": 40,
          "model": "z-ai/glm-5.2",
          "point_rating_method": "sequential_elo",
          "public_id": "E-3916ba303b2ff700",
          "rated_matches": 82,
          "raw_elo_rating": 1575.0888414631513,
          "reasoning": "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": 49.08920702046711,
          "uncertainty": 11.132129994845172,
          "unilateral_faults": 0,
          "wins": 42
        },
        {
          "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": "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": 80,
          "raw_elo_rating": 1624.840786681568,
          "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": 53.73385232288734,
          "uncertainty": 11.805555555555554,
          "unilateral_faults": 0,
          "wins": 38
        }
      ],
      "GB2-06": [
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 82,
          "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": 82,
          "raw_elo_rating": 1877.949290834117,
          "reasoning": "xhigh",
          "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": 93.83172258846857,
          "uncertainty": 11.132129994845172,
          "unilateral_faults": 0,
          "wins": 63
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 92,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 46,
          "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": 1783.3077264160918,
          "reasoning": "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": 84.02163040431354,
          "uncertainty": 8.09758473652126,
          "unilateral_faults": 0,
          "wins": 65
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 104,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 52,
          "draws": 9,
          "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": 42,
          "model": "claude-opus-4-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-1ff6d6f973c7157d",
          "rated_matches": 104,
          "raw_elo_rating": 1549.8531936911686,
          "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": 59.445585881637015,
          "uncertainty": 5.045003647426665,
          "unilateral_faults": 0,
          "wins": 53
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 92,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 46,
          "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": 40,
          "model": "claude-opus-4-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-40a259ca8a40b5b4",
          "rated_matches": 92,
          "raw_elo_rating": 1474.2036667060856,
          "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": 51.13788519283952,
          "uncertainty": 8.09758473652126,
          "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": "legacy_shared_thinking_budget",
          "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": "legacy_shared_thinking_budget",
          "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": 54,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 27,
          "draws": 5,
          "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": 25,
          "model": "claude-opus-4-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-df9bde92610963b7",
          "rated_matches": 54,
          "raw_elo_rating": 1524.5109055238481,
          "reasoning": "high",
          "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": 55.16444931458042,
          "uncertainty": 23.66998624632421,
          "unilateral_faults": 0,
          "wins": 24
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 90,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 45,
          "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": 90,
          "raw_elo_rating": 1774.7289447776332,
          "reasoning": "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": 83.06075814643916,
          "uncertainty": 8.664241836095918,
          "unilateral_faults": 0,
          "wins": 67
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 88,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 44,
          "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": 29,
          "model": "claude-opus-4-8",
          "point_rating_method": "sequential_elo",
          "public_id": "E-db414178442322d3",
          "rated_matches": 88,
          "raw_elo_rating": 1583.0538051265532,
          "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": 62.619735110933746,
          "uncertainty": 9.249894000318006,
          "unilateral_faults": 0,
          "wins": 50
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 80,
          "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": 16,
          "model": "claude-opus-4-8",
          "point_rating_method": "sequential_elo",
          "public_id": "E-e804041031295d93",
          "rated_matches": 80,
          "raw_elo_rating": 1802.081054869981,
          "reasoning": "xhigh",
          "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": 85.7032381321606,
          "uncertainty": 11.805555555555554,
          "unilateral_faults": 0,
          "wins": 62
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 100,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 50,
          "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": 100,
          "raw_elo_rating": 1924.0542264240664,
          "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": 99.17317608622864,
          "uncertainty": 6.001859510499461,
          "unilateral_faults": 0,
          "wins": 84
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 116,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 58,
          "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": 51,
          "model": "claude-sonnet-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-01597b81edc004dd",
          "rated_matches": 116,
          "raw_elo_rating": 1466.154060432485,
          "reasoning": "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": 50.76005671360996,
          "uncertainty": 2.4750163521024238,
          "unilateral_faults": 0,
          "wins": 61
        },
        {
          "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": 1247.029922882203,
          "reasoning": "enabled",
          "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": 26.332638922125277,
          "uncertainty": 15.58908290969266,
          "unilateral_faults": 0,
          "wins": 14
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 82,
          "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": 57,
          "model": "deepseek/deepseek-v4-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-5f5fd61f4544b8d7",
          "rated_matches": 82,
          "raw_elo_rating": 1301.2737990682394,
          "reasoning": "xhigh",
          "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": 32.48264176849661,
          "uncertainty": 11.132129994845172,
          "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": 1404.8183545629643,
          "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": 43.44081870236101,
          "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": 1198.555065024979,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "repaired",
          "score": 21.497692280757313,
          "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": 1177.8349760515114,
          "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": 19.56075363575773,
          "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": 1642.2089240234834,
          "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": 68.86134465387879,
          "uncertainty": 9.855626741889738,
          "unilateral_faults": 0,
          "wins": 54
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 114,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 56,
          "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": 61,
          "model": "deepseek/deepseek-v4-pro",
          "point_rating_method": "sequential_elo",
          "public_id": "E-c9778645f1bbd12c",
          "rated_matches": 114,
          "raw_elo_rating": 1418.5606086737382,
          "reasoning": "xhigh",
          "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": 45.6628100593333,
          "uncertainty": 2.875240412015687,
          "unilateral_faults": 0,
          "wins": 51
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 45,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 23,
          "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": 39,
          "model": "google/gemini-3.1-flash-lite",
          "point_rating_method": "sequential_elo",
          "public_id": "E-6238c7d8dc9e77d9",
          "rated_matches": 45,
          "raw_elo_rating": 1254.5543630538143,
          "reasoning": "high",
          "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": 25.909115893200116,
          "uncertainty": 29.97097807744857,
          "unilateral_faults": 0,
          "wins": 6
        },
        {
          "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-3.1-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": 80,
          "model": "google/gemini-3.1-flash-lite",
          "point_rating_method": "sequential_elo",
          "public_id": "E-a10101fbca309818",
          "rated_matches": 130,
          "raw_elo_rating": 1451.1115221856815,
          "reasoning": "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": 49.375926945379035,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 50
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 78,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 39,
          "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": 34,
          "model": "google/gemini-3.1-flash-lite",
          "point_rating_method": "sequential_elo",
          "public_id": "E-dc1c0f46738d1091",
          "rated_matches": 78,
          "raw_elo_rating": 1432.4590360383802,
          "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": 46.321870346065246,
          "uncertainty": 12.5043950463012,
          "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": 1843.3512911845396,
          "reasoning": "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": 90.25968655583348,
          "uncertainty": 9.855626741889738,
          "unilateral_faults": 0,
          "wins": 63
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 42,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 21,
          "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": "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-5dcb27eaa0273049",
          "rated_matches": 42,
          "raw_elo_rating": 1667.9573138611443,
          "reasoning": "high",
          "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": 69.67342345942932,
          "uncertainty": 32.49928516630233,
          "unilateral_faults": 0,
          "wins": 29
        },
        {
          "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": "low",
          "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": 28,
          "capped_draws": 0,
          "coverage_status": "under_covered",
          "distinct_rated_opponents": 14,
          "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": 17,
          "model": "google/gemini-3.5-flash-lite",
          "point_rating_method": "sequential_elo",
          "public_id": "E-09a450a1726f909a",
          "rated_matches": 28,
          "raw_elo_rating": 1385.6245012441173,
          "reasoning": "high",
          "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": 38.22506944455974,
          "uncertainty": 49.09766908852594,
          "unilateral_faults": 0,
          "wins": 11
        },
        {
          "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": "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": 60,
          "model": "google/gemini-3.5-flash-lite",
          "point_rating_method": "sequential_elo",
          "public_id": "E-3d6c386b0f48e1c1",
          "rated_matches": 70,
          "raw_elo_rating": 1180.741110072107,
          "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": 19.280565801949013,
          "uncertainty": 15.58908290969266,
          "unilateral_faults": 0,
          "wins": 10
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 24,
          "capped_draws": 0,
          "coverage_status": "under_covered",
          "distinct_rated_opponents": 12,
          "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": 10,
          "model": "google/gemini-3.5-flash-lite",
          "point_rating_method": "sequential_elo",
          "public_id": "E-3efea50fdbbd1829",
          "rated_matches": 24,
          "raw_elo_rating": 1621.018317341208,
          "reasoning": "minimal",
          "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": 62.65850437935162,
          "uncertainty": 56.25,
          "unilateral_faults": 0,
          "wins": 14
        },
        {
          "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": "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": 6,
          "model": "google/gemini-3.5-flash-lite",
          "point_rating_method": "sequential_elo",
          "public_id": "E-46f1468c28505bfe",
          "rated_matches": 22,
          "raw_elo_rating": 1669.4100232838757,
          "reasoning": "minimal",
          "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": 67.44429140836692,
          "uncertainty": 60.5072070285374,
          "unilateral_faults": 0,
          "wins": 16
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 24,
          "capped_draws": 0,
          "coverage_status": "under_covered",
          "distinct_rated_opponents": 12,
          "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-3.5-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": 11,
          "model": "google/gemini-3.5-flash-lite",
          "point_rating_method": "sequential_elo",
          "public_id": "E-48cc2611d5aa8816",
          "rated_matches": 24,
          "raw_elo_rating": 1527.0659614938158,
          "reasoning": "high",
          "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": 52.663471203139416,
          "uncertainty": 56.25,
          "unilateral_faults": 0,
          "wins": 11
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 70,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 35,
          "draws": 2,
          "evaluated_setting_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": 53,
          "model": "google/gemini-3.5-flash-lite",
          "point_rating_method": "sequential_elo",
          "public_id": "E-892a28a528dad9c8",
          "rated_matches": 70,
          "raw_elo_rating": 1180.3935957061635,
          "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": 19.243595812367733,
          "uncertainty": 15.58908290969266,
          "unilateral_faults": 0,
          "wins": 15
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 42,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 21,
          "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": "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-280a7de63c992141",
          "rated_matches": 42,
          "raw_elo_rating": 1599.9788656538626,
          "reasoning": "high",
          "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": 62.44160006371974,
          "uncertainty": 32.49928516630233,
          "unilateral_faults": 0,
          "wins": 25
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 66,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 33,
          "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": "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-33485e8cce3184c3",
          "rated_matches": 66,
          "raw_elo_rating": 1822.6642288553644,
          "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": 87.42238761314094,
          "uncertainty": 17.33472217815261,
          "unilateral_faults": 0,
          "wins": 53
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 34,
          "capped_draws": 0,
          "coverage_status": "under_covered",
          "distinct_rated_opponents": 17,
          "draws": 8,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "minimal",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "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-5455742d003ec402",
          "rated_matches": 34,
          "raw_elo_rating": 1466.9183145223224,
          "reasoning": "minimal",
          "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": 47.58256978506472,
          "uncertainty": 40.76542547285167,
          "unilateral_faults": 0,
          "wins": 13
        },
        {
          "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": "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": 3,
          "model": "google/gemini-3.6-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-905531e52a8460f5",
          "rated_matches": 22,
          "raw_elo_rating": 1732.197709542942,
          "reasoning": "high",
          "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": 74.12390046720022,
          "uncertainty": 60.5072070285374,
          "unilateral_faults": 0,
          "wins": 19
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 24,
          "capped_draws": 0,
          "coverage_status": "under_covered",
          "distinct_rated_opponents": 12,
          "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": "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-bb2e288b40b1a588",
          "rated_matches": 24,
          "raw_elo_rating": 1440.9596297120831,
          "reasoning": "minimal",
          "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": 43.503129931460265,
          "uncertainty": 56.25,
          "unilateral_faults": 0,
          "wins": 11
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 66,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 33,
          "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-3.6-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": 4,
          "model": "google/gemini-3.6-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-bdf020e4fa85b365",
          "rated_matches": 66,
          "raw_elo_rating": 1903.1203221826072,
          "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": 95.98163357117124,
          "uncertainty": 17.33472217815261,
          "unilateral_faults": 0,
          "wins": 58
        },
        {
          "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": "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": 53,
          "model": "google/gemma-4-31b-it",
          "point_rating_method": "sequential_elo",
          "public_id": "E-41987f96551bf9d3",
          "rated_matches": 70,
          "raw_elo_rating": 1304.264016556007,
          "reasoning": "enabled",
          "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": 32.421434247378265,
          "uncertainty": 15.58908290969266,
          "unilateral_faults": 0,
          "wins": 17
        },
        {
          "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": 1373.38682774224,
          "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": 40.63225251749573,
          "uncertainty": 5.516463908214657,
          "unilateral_faults": 0,
          "wins": 41
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 88,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 44,
          "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": 34,
          "model": "gpt-4.1",
          "point_rating_method": "sequential_elo",
          "public_id": "E-4dcd6d3653c67437",
          "rated_matches": 88,
          "raw_elo_rating": 1564.774398115172,
          "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": 60.675097556373565,
          "uncertainty": 9.249894000318006,
          "unilateral_faults": 0,
          "wins": 44
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 46,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 23,
          "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": "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": 11,
          "model": "gpt-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-1b082700b3692175",
          "rated_matches": 46,
          "raw_elo_rating": 1686.2801409522417,
          "reasoning": "high",
          "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": 71.90496304115143,
          "uncertainty": 29.182495748947275,
          "unilateral_faults": 0,
          "wins": 31
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 100,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 50,
          "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": 40,
          "model": "gpt-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-816d262cd933cdb9",
          "rated_matches": 100,
          "raw_elo_rating": 1589.115508396417,
          "reasoning": "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": 63.54103500269817,
          "uncertainty": 6.001859510499461,
          "unilateral_faults": 0,
          "wins": 53
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 82,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 41,
          "draws": 8,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "gpt-5.4",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 22,
          "model": "gpt-5.4",
          "point_rating_method": "sequential_elo",
          "public_id": "E-00a57c19a4229948",
          "rated_matches": 82,
          "raw_elo_rating": 1677.2495360528883,
          "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": 72.48046758902608,
          "uncertainty": 11.132129994845172,
          "unilateral_faults": 0,
          "wins": 52
        },
        {
          "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": 1892.891192538813,
          "reasoning": "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": 95.42130277416098,
          "uncertainty": 11.132129994845172,
          "unilateral_faults": 0,
          "wins": 68
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 82,
          "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-5.4",
            "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": 82,
          "raw_elo_rating": 1935.9305085166034,
          "reasoning": "xhigh",
          "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": 11.132129994845172,
          "unilateral_faults": 0,
          "wins": 65
        },
        {
          "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": 1365.4665711563578,
          "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": 39.705796487312476,
          "uncertainty": 6.501890762960602,
          "unilateral_faults": 0,
          "wins": 46
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 106,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 53,
          "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": 42,
          "model": "gpt-5.4-mini",
          "point_rating_method": "sequential_elo",
          "public_id": "E-3ccfe46cbdc271eb",
          "rated_matches": 106,
          "raw_elo_rating": 1574.0883296357088,
          "reasoning": "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": 62.06281243846746,
          "uncertainty": 4.586824452283178,
          "unilateral_faults": 0,
          "wins": 52
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 108,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 54,
          "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": 108,
          "raw_elo_rating": 1654.2541365710636,
          "reasoning": "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": 70.62909269797777,
          "uncertainty": 4.1413142610575715,
          "unilateral_faults": 0,
          "wins": 58
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 102,
          "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": 102,
          "raw_elo_rating": 1563.1232477876315,
          "reasoning": "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": 60.8171834432279,
          "uncertainty": 5.516463908214657,
          "unilateral_faults": 0,
          "wins": 60
        },
        {
          "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": 1397.925943025314,
          "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": 43.20151257567426,
          "uncertainty": 6.001859510499461,
          "unilateral_faults": 0,
          "wins": 45
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 94,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 47,
          "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": 94,
          "raw_elo_rating": 1619.4900816896625,
          "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": 66.64073960908615,
          "uncertainty": 7.54891760425771,
          "unilateral_faults": 0,
          "wins": 62
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 120,
          "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": 72,
          "model": "gpt-5.5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-1ea2c2c23d752166",
          "rated_matches": 120,
          "raw_elo_rating": 1493.0993164354797,
          "reasoning": "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": 53.69217513632242,
          "uncertainty": 1.7045454545454586,
          "unilateral_faults": 0,
          "wins": 47
        },
        {
          "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": "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": 82,
          "raw_elo_rating": 1880.0797890873182,
          "reasoning": "xhigh",
          "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": 94.05837364506577,
          "uncertainty": 11.132129994845172,
          "unilateral_faults": 0,
          "wins": 62
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 84,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 40,
          "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": 84,
          "raw_elo_rating": 1757.888067823131,
          "reasoning": "xhigh",
          "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": 81.11440057033718,
          "uncertainty": 10.482614454664043,
          "unilateral_faults": 0,
          "wins": 52
        },
        {
          "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": 1036.920602437529,
          "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": 4.569710286459858,
          "uncertainty": 8.664241836095918,
          "unilateral_faults": 0,
          "wins": 9
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 106,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 53,
          "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": 106,
          "raw_elo_rating": 1655.1398493340357,
          "reasoning": "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": 70.68540227201106,
          "uncertainty": 4.586824452283178,
          "unilateral_faults": 0,
          "wins": 64
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 98,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 48,
          "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": 57,
          "model": "gpt-5.6-sol",
          "point_rating_method": "sequential_elo",
          "public_id": "E-992b9a5ebbb74c80",
          "rated_matches": 98,
          "raw_elo_rating": 1417.4757599964255,
          "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": 45.23874521686571,
          "uncertainty": 6.501890762960602,
          "unilateral_faults": 0,
          "wins": 38
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 92,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 46,
          "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": 1792.977450720159,
          "reasoning": "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": 85.05033494665588,
          "uncertainty": 8.09758473652126,
          "unilateral_faults": 0,
          "wins": 64
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 84,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 39,
          "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": 84,
          "raw_elo_rating": 1786.9238690390182,
          "reasoning": "xhigh",
          "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": 84.20334702445369,
          "uncertainty": 10.482614454664043,
          "unilateral_faults": 0,
          "wins": 58
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 100,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 49,
          "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": 51,
          "model": "gpt-5.6-terra",
          "point_rating_method": "sequential_elo",
          "public_id": "E-22ffdca36d9bac9c",
          "rated_matches": 100,
          "raw_elo_rating": 1426.7393326842414,
          "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": 46.266797985099174,
          "uncertainty": 6.001859510499461,
          "unilateral_faults": 0,
          "wins": 47
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 100,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 50,
          "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": 41,
          "model": "gpt-5.6-terra",
          "point_rating_method": "sequential_elo",
          "public_id": "E-a3722334e358f0fe",
          "rated_matches": 100,
          "raw_elo_rating": 1507.497978964082,
          "reasoning": "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": 54.85823075496087,
          "uncertainty": 6.001859510499461,
          "unilateral_faults": 0,
          "wins": 47
        },
        {
          "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-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": 90,
          "raw_elo_rating": 1736.344551427424,
          "reasoning": "xhigh",
          "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": 78.97727049438612,
          "uncertainty": 8.664241836095918,
          "unilateral_faults": 0,
          "wins": 56
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 130,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 53,
          "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": 1352.898251283575,
          "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": 38.92760032113381,
          "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": 1302.9988054239868,
          "reasoning": "enabled",
          "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": 31.491832194325372,
          "uncertainty": 24.930281974344517,
          "unilateral_faults": 0,
          "wins": 15
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 128,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 50,
          "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": 987.2524056144644,
          "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": 48,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 24,
          "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": "meituan/longcat-2.0",
            "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 28,
          "model": "meituan/longcat-2.0",
          "point_rating_method": "sequential_elo",
          "public_id": "E-0e252768ba2388c4",
          "rated_matches": 48,
          "raw_elo_rating": 1345.5858403280065,
          "reasoning": "enabled",
          "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": 35.78851456788528,
          "uncertainty": 27.678571428571434,
          "unilateral_faults": 0,
          "wins": 17
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 114,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 55,
          "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": 61,
          "model": "meituan/longcat-2.0",
          "point_rating_method": "sequential_elo",
          "public_id": "E-3e8b2d11481a50d7",
          "rated_matches": 114,
          "raw_elo_rating": 1422.3546000074646,
          "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": 46.06643026564779,
          "uncertainty": 2.875240412015687,
          "unilateral_faults": 0,
          "wins": 47
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 50,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 25,
          "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": "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": 25,
          "model": "meituan/longcat-2.0",
          "point_rating_method": "sequential_elo",
          "public_id": "E-a9bdeb6a9326ac2d",
          "rated_matches": 50,
          "raw_elo_rating": 1411.4177641966762,
          "reasoning": "enabled",
          "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": 42.91237191214209,
          "uncertainty": 26.264004201400486,
          "unilateral_faults": 0,
          "wins": 22
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 94,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 47,
          "draws": 11,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "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": 42,
          "model": "meituan/longcat-2.0",
          "point_rating_method": "sequential_elo",
          "public_id": "E-e3023ff7ecf82fc4",
          "rated_matches": 94,
          "raw_elo_rating": 1534.1588146752608,
          "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": 57.56285287506405,
          "uncertainty": 7.54891760425771,
          "unilateral_faults": 0,
          "wins": 41
        },
        {
          "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": "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": 54,
          "model": "minimax/minimax-m3",
          "point_rating_method": "sequential_elo",
          "public_id": "E-ef8c1a9fa3580f83",
          "rated_matches": 70,
          "raw_elo_rating": 1284.202251048526,
          "reasoning": "enabled",
          "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": 30.287182157453405,
          "uncertainty": 15.58908290969266,
          "unilateral_faults": 0,
          "wins": 16
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 46,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 23,
          "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": 39,
          "model": "mistralai/mistral-medium-3-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-6c35f5ff426e7ada",
          "rated_matches": 46,
          "raw_elo_rating": 1265.0878617129324,
          "reasoning": "high",
          "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": 27.096817821255087,
          "uncertainty": 29.182495748947275,
          "unilateral_faults": 0,
          "wins": 7
        },
        {
          "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": 1378.8243454602684,
          "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": 40.942819015465346,
          "uncertainty": 8.664241836095918,
          "unilateral_faults": 0,
          "wins": 35
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 66,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 33,
          "draws": 4,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "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": 25,
          "model": "moonshotai/kimi-k3",
          "point_rating_method": "sequential_elo",
          "public_id": "E-1640f1438f9390d7",
          "rated_matches": 66,
          "raw_elo_rating": 1534.9056491032766,
          "reasoning": "high",
          "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": 56.80946124827584,
          "uncertainty": 17.33472217815261,
          "unilateral_faults": 0,
          "wins": 37
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 48,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 24,
          "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": "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": 15,
          "model": "moonshotai/kimi-k3",
          "point_rating_method": "sequential_elo",
          "public_id": "E-95a5c0e17cd4b70a",
          "rated_matches": 48,
          "raw_elo_rating": 1593.6276146432358,
          "reasoning": "low",
          "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": 62.17620587170125,
          "uncertainty": 27.678571428571434,
          "unilateral_faults": 0,
          "wins": 31
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 70,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 35,
          "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": "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": 57,
          "model": "nex-agi/nex-n2-pro",
          "point_rating_method": "sequential_elo",
          "public_id": "E-209380b737b62580",
          "rated_matches": 70,
          "raw_elo_rating": 1191.967079496774,
          "reasoning": "enabled",
          "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": 20.47483002047425,
          "uncertainty": 15.58908290969266,
          "unilateral_faults": 0,
          "wins": 8
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 90,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 44,
          "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": 65,
          "model": "nex-agi/nex-n2-pro",
          "point_rating_method": "sequential_elo",
          "public_id": "E-973417dedd770061",
          "rated_matches": 90,
          "raw_elo_rating": 1271.588396713997,
          "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": 29.534623279080066,
          "uncertainty": 8.664241836095918,
          "unilateral_faults": 0,
          "wins": 23
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 96,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 48,
          "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": 96,
          "raw_elo_rating": 1613.9350142082228,
          "reasoning": "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": 66.09501277916272,
          "uncertainty": 7.017308256680951,
          "unilateral_faults": 0,
          "wins": 51
        },
        {
          "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": 1295.593141086351,
          "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": 31.82099690512065,
          "uncertainty": 11.805555555555554,
          "unilateral_faults": 0,
          "wins": 31
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 49,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 25,
          "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": "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": 35,
          "model": "nvidia/nemotron-3-ultra-550b-a55b",
          "point_rating_method": "sequential_elo",
          "public_id": "E-ba2fb1c121873708",
          "rated_matches": 49,
          "raw_elo_rating": 1320.5027486009951,
          "reasoning": "high",
          "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": 33.181171326682524,
          "uncertainty": 26.960678118654744,
          "unilateral_faults": 0,
          "wins": 12
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 30,
          "capped_draws": 0,
          "coverage_status": "under_covered",
          "distinct_rated_opponents": 15,
          "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-03T16:00:00Z",
          "losses": 15,
          "model": "o3",
          "point_rating_method": "sequential_elo",
          "public_id": "E-2c94ff7a30958259",
          "rated_matches": 30,
          "raw_elo_rating": 1473.6395745244195,
          "reasoning": "high",
          "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": 47.84762350013217,
          "uncertainty": 46.05265101338746,
          "unilateral_faults": 0,
          "wins": 15
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 30,
          "capped_draws": 0,
          "coverage_status": "under_covered",
          "distinct_rated_opponents": 15,
          "draws": 2,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "o3",
            "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-03T15:50:00Z",
          "losses": 17,
          "model": "o3",
          "point_rating_method": "sequential_elo",
          "public_id": "E-35751e26cd4e995d",
          "rated_matches": 30,
          "raw_elo_rating": 1409.2273088877162,
          "reasoning": "high",
          "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": 40.99518508933194,
          "uncertainty": 46.05265101338746,
          "unilateral_faults": 0,
          "wins": 11
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 30,
          "capped_draws": 0,
          "coverage_status": "under_covered",
          "distinct_rated_opponents": 15,
          "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 21,
          "model": "o3",
          "point_rating_method": "sequential_elo",
          "public_id": "E-432424671c9fea1c",
          "rated_matches": 30,
          "raw_elo_rating": 1346.2478156014672,
          "reasoning": "high",
          "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": 34.29517081997646,
          "uncertainty": 46.05265101338746,
          "unilateral_faults": 0,
          "wins": 9
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 102,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 51,
          "draws": 10,
          "evaluated_setting_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-69e964db7b91b1bb",
          "rated_matches": 102,
          "raw_elo_rating": 1607.5937026330773,
          "reasoning": "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": 65.54813103397758,
          "uncertainty": 5.516463908214657,
          "unilateral_faults": 0,
          "wins": 50
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 46,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 23,
          "draws": 12,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "low",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "o3",
            "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-21T14:20:15Z",
          "losses": 21,
          "model": "o3",
          "point_rating_method": "sequential_elo",
          "public_id": "E-9f2773793ec1d7e3",
          "rated_matches": 46,
          "raw_elo_rating": 1386.3188740171406,
          "reasoning": "low",
          "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": 39.99386525596274,
          "uncertainty": 29.182495748947275,
          "unilateral_faults": 0,
          "wins": 13
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 28,
          "capped_draws": 0,
          "coverage_status": "under_covered",
          "distinct_rated_opponents": 14,
          "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-03T15:45:00Z",
          "losses": 14,
          "model": "o3",
          "point_rating_method": "sequential_elo",
          "public_id": "E-ead4229a85e5d554",
          "rated_matches": 28,
          "raw_elo_rating": 1478.8537747463809,
          "reasoning": "high",
          "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": 48.14317818430083,
          "uncertainty": 49.09766908852594,
          "unilateral_faults": 0,
          "wins": 13
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 50,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 25,
          "draws": 4,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "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": 18,
          "model": "openai/gpt-oss-120b",
          "point_rating_method": "sequential_elo",
          "public_id": "E-a97b527d9b41a80c",
          "rated_matches": 50,
          "raw_elo_rating": 1619.371511306429,
          "reasoning": "high",
          "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": 65.03533607555016,
          "uncertainty": 26.264004201400486,
          "unilateral_faults": 0,
          "wins": 28
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 60,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 30,
          "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": 32,
          "model": "openai/gpt-oss-120b",
          "point_rating_method": "sequential_elo",
          "public_id": "E-b75de88bfc62ab22",
          "rated_matches": 60,
          "raw_elo_rating": 1489.7264897089944,
          "reasoning": "low",
          "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": 51.753438139182734,
          "uncertainty": 20.268439966447993,
          "unilateral_faults": 0,
          "wins": 28
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 121,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 61,
          "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": 1384.137730967665,
          "reasoning": "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": 42.11628633456594,
          "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": 1270.3210113293824,
          "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": 29.784727597962565,
          "uncertainty": 4.1413142610575715,
          "unilateral_faults": 0,
          "wins": 46
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 48,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 24,
          "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": "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": 29,
          "model": "poolside/laguna-s-2.1",
          "point_rating_method": "sequential_elo",
          "public_id": "E-b582570ce841ee30",
          "rated_matches": 48,
          "raw_elo_rating": 1331.9790233058707,
          "reasoning": "enabled",
          "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": 34.34096611279594,
          "uncertainty": 27.678571428571434,
          "unilateral_faults": 0,
          "wins": 18
        },
        {
          "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": 1279.3223943837968,
          "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": 30.541429111812185,
          "uncertainty": 6.501890762960602,
          "unilateral_faults": 0,
          "wins": 33
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 70,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 35,
          "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-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": 25,
          "model": "qwen/qwen3.7-max",
          "point_rating_method": "sequential_elo",
          "public_id": "E-8283efe6f68a787e",
          "rated_matches": 70,
          "raw_elo_rating": 1615.2240279036346,
          "reasoning": "enabled",
          "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": 65.50262313148998,
          "uncertainty": 15.58908290969266,
          "unilateral_faults": 0,
          "wins": 40
        },
        {
          "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": 1276.4806787457837,
          "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": 30.26055359128659,
          "uncertainty": 6.25,
          "unilateral_faults": 0,
          "wins": 26
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 62,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 31,
          "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": "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": 12,
          "model": "qwen/qwen3.7-plus",
          "point_rating_method": "sequential_elo",
          "public_id": "E-b6dd11ebe2b80c7b",
          "rated_matches": 62,
          "raw_elo_rating": 1768.9651446619,
          "reasoning": "enabled",
          "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": 81.54716086048992,
          "uncertainty": 19.244078834871203,
          "unilateral_faults": 0,
          "wins": 47
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 50,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 25,
          "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": "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": 39,
          "model": "stepfun/step-3.7-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-2d684425ca56be18",
          "rated_matches": 50,
          "raw_elo_rating": 1316.16547310662,
          "reasoning": "high",
          "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": 32.779046345492574,
          "uncertainty": 26.264004201400486,
          "unilateral_faults": 0,
          "wins": 10
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 110,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 55,
          "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": 76,
          "model": "stepfun/step-3.7-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-6526762dce98da7c",
          "rated_matches": 110,
          "raw_elo_rating": 1299.6101532628288,
          "reasoning": "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": 32.937512179985525,
          "uncertainty": 3.707899787624953,
          "unilateral_faults": 0,
          "wins": 33
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 46,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 23,
          "draws": 3,
          "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": 14,
          "model": "stepfun/step-3.7-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-ab4ccc8ca01bc627",
          "rated_matches": 46,
          "raw_elo_rating": 1623.016874040932,
          "reasoning": "low",
          "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": 65.17475978109492,
          "uncertainty": 29.182495748947275,
          "unilateral_faults": 0,
          "wins": 29
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 42,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 21,
          "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": 36,
          "model": "tencent/hy3-preview",
          "point_rating_method": "sequential_elo",
          "public_id": "E-3627e3dbf7a48738",
          "rated_matches": 42,
          "raw_elo_rating": 1269.8921642421287,
          "reasoning": "high",
          "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": 27.325636212896253,
          "uncertainty": 32.49928516630233,
          "unilateral_faults": 0,
          "wins": 6
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 110,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 53,
          "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": 56,
          "model": "thinkingmachines/inkling",
          "point_rating_method": "sequential_elo",
          "public_id": "E-02be9616e86c7055",
          "rated_matches": 110,
          "raw_elo_rating": 1364.1456650071532,
          "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": 39.80306201224402,
          "uncertainty": 3.707899787624953,
          "unilateral_faults": 0,
          "wins": 53
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 26,
          "capped_draws": 0,
          "coverage_status": "under_covered",
          "distinct_rated_opponents": 13,
          "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": 12,
          "model": "thinkingmachines/inkling",
          "point_rating_method": "sequential_elo",
          "public_id": "E-56e54327930d2f64",
          "rated_matches": 26,
          "raw_elo_rating": 1513.8216182614226,
          "reasoning": "max",
          "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": 51.575760228440956,
          "uncertainty": 52.475044864937615,
          "unilateral_faults": 0,
          "wins": 14
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 120,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 60,
          "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": 61,
          "model": "x-ai/grok-4.5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-3baaff3521870bef",
          "rated_matches": 120,
          "raw_elo_rating": 1442.0865376108627,
          "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": 48.2652285508529,
          "uncertainty": 1.7045454545454586,
          "unilateral_faults": 0,
          "wins": 51
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 44,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 22,
          "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": "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": 22,
          "model": "x-ai/grok-4.5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-5a1e23bce371a184",
          "rated_matches": 44,
          "raw_elo_rating": 1503.5914373587705,
          "reasoning": "high",
          "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": 52.33336108510253,
          "uncertainty": 30.785599249992988,
          "unilateral_faults": 0,
          "wins": 19
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 42,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 21,
          "draws": 7,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "low",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "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": 12,
          "model": "x-ai/grok-4.5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-8dbfeb56f012d9c6",
          "rated_matches": 42,
          "raw_elo_rating": 1579.5168804285463,
          "reasoning": "low",
          "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": 60.26477097483131,
          "uncertainty": 32.49928516630233,
          "unilateral_faults": 0,
          "wins": 23
        },
        {
          "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": "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": 48,
          "model": "x-ai/grok-build-0.1",
          "point_rating_method": "sequential_elo",
          "public_id": "E-133675db0ee21fd5",
          "rated_matches": 70,
          "raw_elo_rating": 1347.5318338568136,
          "reasoning": "enabled",
          "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": 37.024440371953844,
          "uncertainty": 15.58908290969266,
          "unilateral_faults": 0,
          "wins": 22
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 68,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 34,
          "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": "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": 28,
          "model": "xiaomi/mimo-v2.5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-51421c7ae2af8f7b",
          "rated_matches": 68,
          "raw_elo_rating": 1588.8776884828033,
          "reasoning": "high",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "repaired",
          "score": 62.62712426295049,
          "uncertainty": 16.4429265428846,
          "unilateral_faults": 0,
          "wins": 34
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 70,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 35,
          "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": "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": 52,
          "model": "xiaomi/mimo-v2.5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-7b4c450b6850f156",
          "rated_matches": 70,
          "raw_elo_rating": 1291.0631630919836,
          "reasoning": "enabled",
          "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": 31.01707384430817,
          "uncertainty": 15.58908290969266,
          "unilateral_faults": 0,
          "wins": 14
        },
        {
          "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": 1370.0835377541052,
          "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": 40.23952442879587,
          "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": 1398.3402844497405,
          "reasoning": "none",
          "reasoning_bracket": "baseline",
          "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "none",
          "repair_status": "repaired",
          "score": 42.80896869171179,
          "uncertainty": 11.132129994845172,
          "unilateral_faults": 0,
          "wins": 34
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 84,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 42,
          "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": 84,
          "raw_elo_rating": 1630.4513120878032,
          "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": 67.55716094653901,
          "uncertainty": 10.482614454664043,
          "unilateral_faults": 0,
          "wins": 51
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 62,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 31,
          "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": 17,
          "model": "xiaomi/mimo-v2.5-pro",
          "point_rating_method": "sequential_elo",
          "public_id": "E-530f82d65699c577",
          "rated_matches": 62,
          "raw_elo_rating": 1690.6528962825803,
          "reasoning": "enabled",
          "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": 73.21598583464518,
          "uncertainty": 19.244078834871203,
          "unilateral_faults": 0,
          "wins": 45
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 100,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 50,
          "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": 44,
          "model": "xiaomi/mimo-v2.5-pro",
          "point_rating_method": "sequential_elo",
          "public_id": "E-6b662c734cdcff91",
          "rated_matches": 100,
          "raw_elo_rating": 1441.8800041097018,
          "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": 47.87752410093403,
          "uncertainty": 6.001859510499461,
          "unilateral_faults": 0,
          "wins": 55
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 74,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 37,
          "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": 29,
          "model": "z-ai/glm-5.2",
          "point_rating_method": "sequential_elo",
          "public_id": "E-657c61c9039ce566",
          "rated_matches": 74,
          "raw_elo_rating": 1525.1488052535287,
          "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": 56.05657192326941,
          "uncertainty": 13.985026918962571,
          "unilateral_faults": 0,
          "wins": 35
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 68,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 34,
          "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": "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": 68,
          "raw_elo_rating": 1655.2045242420968,
          "reasoning": "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": 69.68324241888193,
          "uncertainty": 16.4429265428846,
          "unilateral_faults": 0,
          "wins": 35
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 70,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 35,
          "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": 70,
          "raw_elo_rating": 1681.9707996856102,
          "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": 72.60341578696683,
          "uncertainty": 15.58908290969266,
          "unilateral_faults": 0,
          "wins": 31
        }
      ],
      "GB2-07": [
        {
          "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": "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": 90,
          "raw_elo_rating": 1713.9112383774284,
          "reasoning": "xhigh",
          "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": 66.9670189086873,
          "uncertainty": 8.664241836095918,
          "unilateral_faults": 0,
          "wins": 55
        },
        {
          "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": 1762.4042745072609,
          "reasoning": "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": 71.79611330973476,
          "uncertainty": 8.664241836095918,
          "unilateral_faults": 0,
          "wins": 70
        },
        {
          "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": "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": 51,
          "model": "claude-opus-4-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-ca22621c58b6f244",
          "rated_matches": 108,
          "raw_elo_rating": 1532.1958341337388,
          "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": 49.231533682902075,
          "uncertainty": 4.1413142610575715,
          "unilateral_faults": 0,
          "wins": 57
        },
        {
          "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": "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": 55,
          "model": "claude-opus-4-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-e7848fdc8b4ffd95",
          "rated_matches": 104,
          "raw_elo_rating": 1484.9594600967189,
          "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": 44.455587919211716,
          "uncertainty": 5.045003647426665,
          "unilateral_faults": 0,
          "wins": 49
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 50,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 25,
          "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": 28,
          "model": "claude-opus-4-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-e8719bed57f17312",
          "rated_matches": 50,
          "raw_elo_rating": 1450.1460873197461,
          "reasoning": "high",
          "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": 39.29831320648614,
          "uncertainty": 26.264004201400486,
          "unilateral_faults": 0,
          "wins": 22
        },
        {
          "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": "legacy_shared_thinking_budget",
          "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": "legacy_shared_thinking_budget",
          "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": 100,
          "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-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": 100,
          "raw_elo_rating": 1667.8017327798075,
          "reasoning": "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": 62.58738719657233,
          "uncertainty": 6.001859510499461,
          "unilateral_faults": 0,
          "wins": 66
        },
        {
          "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": "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": 90,
          "raw_elo_rating": 1803.2582355928973,
          "reasoning": "xhigh",
          "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": 75.86448374979243,
          "uncertainty": 8.664241836095918,
          "unilateral_faults": 0,
          "wins": 69
        },
        {
          "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": "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": 35,
          "model": "claude-opus-4-8",
          "point_rating_method": "sequential_elo",
          "public_id": "E-76804598cce96e62",
          "rated_matches": 92,
          "raw_elo_rating": 1576.1603536781683,
          "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": 53.294481025847816,
          "uncertainty": 8.09758473652126,
          "unilateral_faults": 0,
          "wins": 57
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 78,
          "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": 78,
          "raw_elo_rating": 2048.6955646228785,
          "reasoning": "xhigh",
          "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": 12.5043950463012,
          "unilateral_faults": 0,
          "wins": 77
        },
        {
          "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": "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": 84,
          "raw_elo_rating": 1979.410637944388,
          "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": 93.26144984700437,
          "uncertainty": 10.482614454664043,
          "unilateral_faults": 0,
          "wins": 79
        },
        {
          "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-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": 96,
          "raw_elo_rating": 1835.2604164135125,
          "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": 79.18257070094032,
          "uncertainty": 7.017308256680951,
          "unilateral_faults": 0,
          "wins": 74
        },
        {
          "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": 28,
          "model": "claude-opus-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-de5e72176c4f0dc9",
          "rated_matches": 104,
          "raw_elo_rating": 1815.7391470039968,
          "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": 77.39570595487102,
          "uncertainty": 5.045003647426665,
          "unilateral_faults": 0,
          "wins": 76
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 122,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 61,
          "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": 50,
          "model": "claude-sonnet-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-9e40526fba9fa8b9",
          "rated_matches": 122,
          "raw_elo_rating": 1548.1539016254237,
          "reasoning": "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": 51.044380476224916,
          "uncertainty": 1.3334817333716131,
          "unilateral_faults": 0,
          "wins": 72
        },
        {
          "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": 1399.0487098290237,
          "reasoning": "enabled",
          "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": 35.248221907515756,
          "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": 1477.8028209416357,
          "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": 43.66667703715262,
          "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": 1126.4180876957776,
          "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": 8.462538450612445,
          "uncertainty": 8.664241836095918,
          "unilateral_faults": 4,
          "wins": 11
        },
        {
          "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": "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": 47,
          "model": "deepseek/deepseek-v4-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-8f2f6c973751f183",
          "rated_matches": 74,
          "raw_elo_rating": 1380.9199425547763,
          "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": 33.38277277782705,
          "uncertainty": 13.985026918962571,
          "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": 1406.6667442109426,
          "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": 36.22574841026145,
          "uncertainty": 10.482614454664043,
          "unilateral_faults": 0,
          "wins": 36
        },
        {
          "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": "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-ecf2a6ea6f9fe06c",
          "rated_matches": 92,
          "raw_elo_rating": 1741.0405753174614,
          "reasoning": "xhigh",
          "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": 69.71379024439247,
          "uncertainty": 8.09758473652126,
          "unilateral_faults": 0,
          "wins": 63
        },
        {
          "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": "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": 39,
          "model": "deepseek/deepseek-v4-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-edc2d085c4253ed3",
          "rated_matches": 74,
          "raw_elo_rating": 1530.8826673809547,
          "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": 48.316549101607485,
          "uncertainty": 13.985026918962571,
          "unilateral_faults": 0,
          "wins": 35
        },
        {
          "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": "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": 52,
          "model": "deepseek/deepseek-v4-pro",
          "point_rating_method": "sequential_elo",
          "public_id": "E-f398fd6ac8c8bada",
          "rated_matches": 96,
          "raw_elo_rating": 1592.3030320455705,
          "reasoning": "xhigh",
          "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": 54.98808344707694,
          "uncertainty": 7.017308256680951,
          "unilateral_faults": 0,
          "wins": 44
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 98,
          "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": "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": 42,
          "model": "deepseek/deepseek-v4-pro",
          "point_rating_method": "sequential_elo",
          "public_id": "E-f76d96b0f3163d4b",
          "rated_matches": 98,
          "raw_elo_rating": 1486.6131615979011,
          "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": 44.504203648777164,
          "uncertainty": 6.501890762960602,
          "unilateral_faults": 0,
          "wins": 56
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 50,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 25,
          "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": 39,
          "model": "google/gemini-3.1-flash-lite",
          "point_rating_method": "sequential_elo",
          "public_id": "E-0d43f308cfa4da52",
          "rated_matches": 50,
          "raw_elo_rating": 1334.9311531054598,
          "reasoning": "high",
          "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": 27.824834989085325,
          "uncertainty": 26.264004201400486,
          "unilateral_faults": 0,
          "wins": 11
        },
        {
          "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": "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": 80,
          "model": "google/gemini-3.1-flash-lite",
          "point_rating_method": "sequential_elo",
          "public_id": "E-1b3c52da51dfbdd4",
          "rated_matches": 92,
          "raw_elo_rating": 1052.903259206907,
          "reasoning": "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": 1.18683615794815,
          "uncertainty": 8.09758473652126,
          "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": 1045.6951836273022,
          "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": 106,
          "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": 51,
          "model": "google/gemini-3.5-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-5447c508e2b0ab6c",
          "rated_matches": 106,
          "raw_elo_rating": 1583.0678904088375,
          "reasoning": "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": 54.26204637051112,
          "uncertainty": 4.586824452283178,
          "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": "low",
          "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": 46,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 23,
          "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": 19,
          "model": "google/gemini-3.5-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-f7f306cca2bb9532",
          "rated_matches": 46,
          "raw_elo_rating": 1614.5960622689374,
          "reasoning": "high",
          "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": 55.44227074773221,
          "uncertainty": 29.182495748947275,
          "unilateral_faults": 0,
          "wins": 27
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 20,
          "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": "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": 14,
          "model": "google/gemini-3.5-flash-lite",
          "point_rating_method": "sequential_elo",
          "public_id": "E-455ee67905f5f955",
          "rated_matches": 20,
          "raw_elo_rating": 1456.0840723741392,
          "reasoning": "minimal",
          "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": 36.775075900320765,
          "uncertainty": 65.3589451179962,
          "unilateral_faults": 0,
          "wins": 6
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 40,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 20,
          "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": 26,
          "model": "google/gemini-3.5-flash-lite",
          "point_rating_method": "sequential_elo",
          "public_id": "E-c4d27e5c752afb39",
          "rated_matches": 40,
          "raw_elo_rating": 1422.0317210539686,
          "reasoning": "high",
          "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": 35.85545441373769,
          "uncertainty": 34.33688094430304,
          "unilateral_faults": 0,
          "wins": 14
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 20,
          "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": "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": 4,
          "model": "google/gemini-3.5-flash-lite",
          "point_rating_method": "sequential_elo",
          "public_id": "E-e2e240babaf0b862",
          "rated_matches": 20,
          "raw_elo_rating": 1676.1076487053144,
          "reasoning": "minimal",
          "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": 58.685739891632934,
          "uncertainty": 65.3589451179962,
          "unilateral_faults": 0,
          "wins": 16
        },
        {
          "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": "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": 48,
          "model": "google/gemini-3.5-flash-lite",
          "point_rating_method": "sequential_elo",
          "public_id": "E-f74134262b66367b",
          "rated_matches": 70,
          "raw_elo_rating": 1257.5590178307139,
          "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": 20.97030061327731,
          "uncertainty": 15.58908290969266,
          "unilateral_faults": 0,
          "wins": 22
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 44,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 22,
          "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": 28,
          "model": "google/gemini-3.5-flash-lite",
          "point_rating_method": "sequential_elo",
          "public_id": "E-f746ec3aee7874b2",
          "rated_matches": 44,
          "raw_elo_rating": 1420.1759752219925,
          "reasoning": "high",
          "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": 35.95357175614385,
          "uncertainty": 30.785599249992988,
          "unilateral_faults": 0,
          "wins": 16
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 68,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 34,
          "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": 32,
          "model": "google/gemini-3.6-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-1f7519ff2c4a840c",
          "rated_matches": 68,
          "raw_elo_rating": 1638.7684416591005,
          "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": 58.864353196612875,
          "uncertainty": 16.4429265428846,
          "unilateral_faults": 0,
          "wins": 36
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 128,
          "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": 53,
          "model": "google/gemini-3.6-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-65c6c8e09fe2c210",
          "rated_matches": 128,
          "raw_elo_rating": 1490.1292333854794,
          "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": 45.35061632230381,
          "uncertainty": 0.27254531628119416,
          "unilateral_faults": 0,
          "wins": 75
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 26,
          "capped_draws": 0,
          "coverage_status": "under_covered",
          "distinct_rated_opponents": 11,
          "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": 9,
          "model": "google/gemini-3.6-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-8e9b51be911dad38",
          "rated_matches": 22,
          "raw_elo_rating": 1512.9516514437669,
          "reasoning": "minimal",
          "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": 42.82465604818685,
          "uncertainty": 60.5072070285374,
          "unilateral_faults": 0,
          "wins": 13
        },
        {
          "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": "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": 6,
          "model": "google/gemini-3.6-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-a2d90fcdc2f4ef9d",
          "rated_matches": 22,
          "raw_elo_rating": 1638.6834635651658,
          "reasoning": "minimal",
          "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": 55.345439204007334,
          "uncertainty": 60.5072070285374,
          "unilateral_faults": 0,
          "wins": 16
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 47,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 24,
          "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": 24,
          "model": "google/gemini-3.6-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-f6ecc1626f38fa34",
          "rated_matches": 47,
          "raw_elo_rating": 1535.5674257043515,
          "reasoning": "high",
          "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": 47.63318420011444,
          "uncertainty": 28.418783648703226,
          "unilateral_faults": 0,
          "wins": 23
        },
        {
          "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": 1288.3055324602838,
          "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": 24.48890361547792,
          "uncertainty": 9.855626741889738,
          "unilateral_faults": 2,
          "wins": 27
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 66,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 33,
          "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": 43,
          "model": "google/gemma-4-31b-it",
          "point_rating_method": "sequential_elo",
          "public_id": "E-f417d302c870dfa6",
          "rated_matches": 66,
          "raw_elo_rating": 1349.313649651218,
          "reasoning": "enabled",
          "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": 29.96845639325902,
          "uncertainty": 17.33472217815261,
          "unilateral_faults": 0,
          "wins": 23
        },
        {
          "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": "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": 45,
          "model": "gpt-4.1",
          "point_rating_method": "sequential_elo",
          "public_id": "E-fcfa606d3cbb0ba0",
          "rated_matches": 84,
          "raw_elo_rating": 1549.1610657525957,
          "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": 50.41579682248144,
          "uncertainty": 10.482614454664043,
          "unilateral_faults": 0,
          "wins": 39
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 54,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 27,
          "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": 28,
          "model": "gpt-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-15dad0db253c0497",
          "rated_matches": 54,
          "raw_elo_rating": 1511.696585516207,
          "reasoning": "high",
          "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": 45.63436878910724,
          "uncertainty": 23.66998624632421,
          "unilateral_faults": 0,
          "wins": 26
        },
        {
          "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",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_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",
          "point_rating_method": "sequential_elo",
          "public_id": "E-4d8b4cfcff519db6",
          "rated_matches": 98,
          "raw_elo_rating": 1638.5757431946397,
          "reasoning": "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": 59.63713222006284,
          "uncertainty": 6.501890762960602,
          "unilateral_faults": 0,
          "wins": 59
        },
        {
          "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": "low",
          "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": 100,
          "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-5.4",
            "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": 100,
          "raw_elo_rating": 1645.147005295843,
          "reasoning": "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": 60.331355683982295,
          "uncertainty": 6.001859510499461,
          "unilateral_faults": 0,
          "wins": 65
        },
        {
          "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-5.4",
            "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": 96,
          "raw_elo_rating": 1934.857523033671,
          "reasoning": "xhigh",
          "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": 89.10077480456111,
          "uncertainty": 7.017308256680951,
          "unilateral_faults": 0,
          "wins": 85
        },
        {
          "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": 1299.2820176175837,
          "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": 25.63023441070387,
          "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": 1144.1874341325886,
          "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": 10.185410895530666,
          "uncertainty": 9.249894000318006,
          "unilateral_faults": 2,
          "wins": 14
        },
        {
          "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": "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": 106,
          "raw_elo_rating": 1545.2161928372725,
          "reasoning": "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": 50.492651104691994,
          "uncertainty": 4.586824452283178,
          "unilateral_faults": 0,
          "wins": 58
        },
        {
          "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": 1377.7199812397787,
          "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": 33.70010205201074,
          "uncertainty": 6.001859510499461,
          "unilateral_faults": 0,
          "wins": 38
        },
        {
          "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": "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": 1200.2033445884742,
          "reasoning": "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": 15.899168625252624,
          "uncertainty": 7.54891760425771,
          "unilateral_faults": 0,
          "wins": 16
        },
        {
          "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-5.4-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": 34,
          "model": "gpt-5.4-nano",
          "point_rating_method": "sequential_elo",
          "public_id": "E-ce04fd14b6f43868",
          "rated_matches": 98,
          "raw_elo_rating": 1643.5092706977405,
          "reasoning": "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": 60.12842894932622,
          "uncertainty": 6.501890762960602,
          "unilateral_faults": 0,
          "wins": 64
        },
        {
          "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": "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": 50,
          "model": "gpt-5.5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-4edfe4117ad3e936",
          "rated_matches": 108,
          "raw_elo_rating": 1517.5057890966405,
          "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": 47.768651176435434,
          "uncertainty": 4.1413142610575715,
          "unilateral_faults": 0,
          "wins": 58
        },
        {
          "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": "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": 96,
          "raw_elo_rating": 1964.5526124609985,
          "reasoning": "xhigh",
          "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": 92.05790847852163,
          "uncertainty": 7.017308256680951,
          "unilateral_faults": 0,
          "wins": 90
        },
        {
          "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": "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": 1732.0611905000076,
          "reasoning": "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": 68.86330432028504,
          "uncertainty": 7.54891760425771,
          "unilateral_faults": 0,
          "wins": 62
        },
        {
          "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": "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": 62,
          "model": "gpt-5.6-luna",
          "point_rating_method": "sequential_elo",
          "public_id": "E-45c76cf9faaba10a",
          "rated_matches": 112,
          "raw_elo_rating": 1521.5171741625923,
          "reasoning": "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": 48.23625448361621,
          "uncertainty": 3.286043419179858,
          "unilateral_faults": 0,
          "wins": 50
        },
        {
          "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-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": 28,
          "model": "gpt-5.6-luna",
          "point_rating_method": "sequential_elo",
          "public_id": "E-73a7b73c1df452ad",
          "rated_matches": 92,
          "raw_elo_rating": 1808.0596113105762,
          "reasoning": "xhigh",
          "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": 76.38776402098694,
          "uncertainty": 8.09758473652126,
          "unilateral_faults": 0,
          "wins": 64
        },
        {
          "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": 1172.2216045615141,
          "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": 12.928888178071984,
          "uncertainty": 9.855626741889738,
          "unilateral_faults": 1,
          "wins": 17
        },
        {
          "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": "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": 29,
          "model": "gpt-5.6-sol",
          "point_rating_method": "sequential_elo",
          "public_id": "E-1b522c9c14f3860c",
          "rated_matches": 92,
          "raw_elo_rating": 1633.041024252725,
          "reasoning": "xhigh",
          "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": 58.95884336983468,
          "uncertainty": 8.09758473652126,
          "unilateral_faults": 0,
          "wins": 63
        },
        {
          "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-5.6-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-bef852aad169a609",
          "rated_matches": 90,
          "raw_elo_rating": 1667.940513626986,
          "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": 62.3891044858804,
          "uncertainty": 8.664241836095918,
          "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": 1641.3171931289405,
          "reasoning": "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": 59.9101347289806,
          "uncertainty": 6.501890762960602,
          "unilateral_faults": 0,
          "wins": 60
        },
        {
          "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": "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": 92,
          "raw_elo_rating": 1761.1968899835726,
          "reasoning": "xhigh",
          "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": 71.72102167529864,
          "uncertainty": 8.09758473652126,
          "unilateral_faults": 0,
          "wins": 63
        },
        {
          "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": "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": 58,
          "model": "gpt-5.6-terra",
          "point_rating_method": "sequential_elo",
          "public_id": "E-8ebe8776c7d44d46",
          "rated_matches": 106,
          "raw_elo_rating": 1445.8694948539608,
          "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": 40.59938350830355,
          "uncertainty": 4.586824452283178,
          "unilateral_faults": 0,
          "wins": 48
        },
        {
          "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": "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": 1401.2822756940366,
          "reasoning": "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": 36.2955991645047,
          "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": 1496.9801801957265,
          "reasoning": "enabled",
          "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": 44.0684577587389,
          "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": 1429.9790809110914,
          "reasoning": "enabled",
          "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": 37.39627017796564,
          "uncertainty": 24.930281974344517,
          "unilateral_faults": 0,
          "wins": 19
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 50,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 25,
          "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
            "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": "meituan/longcat-2.0",
          "point_rating_method": "sequential_elo",
          "public_id": "E-28ec7bff448d69bb",
          "rated_matches": 50,
          "raw_elo_rating": 1710.7882394632145,
          "reasoning": "enabled",
          "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": 65.25390720606802,
          "uncertainty": 26.264004201400486,
          "unilateral_faults": 0,
          "wins": 34
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 98,
          "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": "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": 45,
          "model": "meituan/longcat-2.0",
          "point_rating_method": "sequential_elo",
          "public_id": "E-c1f595f47c71e648",
          "rated_matches": 98,
          "raw_elo_rating": 1427.0152922360796,
          "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": 38.56925380404107,
          "uncertainty": 6.501890762960602,
          "unilateral_faults": 0,
          "wins": 53
        },
        {
          "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": "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": 54,
          "model": "meituan/longcat-2.0",
          "point_rating_method": "sequential_elo",
          "public_id": "E-e2db910734ca5315",
          "rated_matches": 104,
          "raw_elo_rating": 1492.5125839523562,
          "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": 45.20775258104111,
          "uncertainty": 5.045003647426665,
          "unilateral_faults": 0,
          "wins": 50
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 44,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 22,
          "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": 33,
          "model": "meituan/longcat-2.0",
          "point_rating_method": "sequential_elo",
          "public_id": "E-fe21773d3155f05f",
          "rated_matches": 44,
          "raw_elo_rating": 1234.8618172648503,
          "reasoning": "enabled",
          "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": 17.499384638849104,
          "uncertainty": 30.785599249992988,
          "unilateral_faults": 0,
          "wins": 11
        },
        {
          "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": 1440.0116718921627,
          "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": 39.64455151180685,
          "uncertainty": 9.249894000318006,
          "unilateral_faults": 0,
          "wins": 37
        },
        {
          "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": "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": 34,
          "model": "minimax/minimax-m3",
          "point_rating_method": "sequential_elo",
          "public_id": "E-4547f4cedca403f9",
          "rated_matches": 74,
          "raw_elo_rating": 1558.812989789706,
          "reasoning": "enabled",
          "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": 51.0979415308717,
          "uncertainty": 13.985026918962571,
          "unilateral_faults": 0,
          "wins": 40
        },
        {
          "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": "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": 50,
          "model": "mistralai/mistral-medium-3-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-d0d0df9d83b6e37e",
          "rated_matches": 52,
          "raw_elo_rating": 1166.352764344129,
          "reasoning": "high",
          "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": 11.143503370504328,
          "uncertainty": 24.930281974344517,
          "unilateral_faults": 0,
          "wins": 2
        },
        {
          "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": "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": 32,
          "model": "moonshotai/kimi-k2.7-code",
          "point_rating_method": "sequential_elo",
          "public_id": "E-d35e87ebfc251f60",
          "rated_matches": 76,
          "raw_elo_rating": 1583.9094538021247,
          "reasoning": "enabled",
          "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": 53.65725658424505,
          "uncertainty": 13.230288229818967,
          "unilateral_faults": 0,
          "wins": 44
        },
        {
          "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": "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": 22,
          "model": "moonshotai/kimi-k3",
          "point_rating_method": "sequential_elo",
          "public_id": "E-1d1372c78963efdf",
          "rated_matches": 52,
          "raw_elo_rating": 1621.2324506288412,
          "reasoning": "max",
          "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": 56.441903336770274,
          "uncertainty": 24.930281974344517,
          "unilateral_faults": 0,
          "wins": 30
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 48,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 24,
          "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": 26,
          "model": "moonshotai/kimi-k3",
          "point_rating_method": "sequential_elo",
          "public_id": "E-4d8815930b656774",
          "rated_matches": 48,
          "raw_elo_rating": 1436.117544167627,
          "reasoning": "low",
          "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": 37.78861144361751,
          "uncertainty": 27.678571428571434,
          "unilateral_faults": 0,
          "wins": 22
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 44,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 22,
          "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": 29,
          "model": "moonshotai/kimi-k3",
          "point_rating_method": "sequential_elo",
          "public_id": "E-55ef4536a723bcf7",
          "rated_matches": 44,
          "raw_elo_rating": 1385.765880772664,
          "reasoning": "high",
          "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": 32.5269025329615,
          "uncertainty": 30.785599249992988,
          "unilateral_faults": 0,
          "wins": 15
        },
        {
          "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": "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": 92,
          "raw_elo_rating": 1633.70258494576,
          "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": 59.024723737278265,
          "uncertainty": 8.09758473652126,
          "unilateral_faults": 0,
          "wins": 63
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 66,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 33,
          "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": 43,
          "model": "nex-agi/nex-n2-pro",
          "point_rating_method": "sequential_elo",
          "public_id": "E-d1f432cda667f27f",
          "rated_matches": 66,
          "raw_elo_rating": 1363.3468730726593,
          "reasoning": "enabled",
          "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": 31.36593046503488,
          "uncertainty": 17.33472217815261,
          "unilateral_faults": 0,
          "wins": 23
        },
        {
          "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": 1179.1916405345034,
          "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": 13.294011760456632,
          "uncertainty": 13.985026918962571,
          "unilateral_faults": 0,
          "wins": 12
        },
        {
          "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": "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": 1165.7290719890677,
          "reasoning": "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": 12.422397885640807,
          "uncertainty": 8.09758473652126,
          "unilateral_faults": 0,
          "wins": 20
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 46,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 23,
          "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-03T15:50:00Z",
          "losses": 29,
          "model": "o3",
          "point_rating_method": "sequential_elo",
          "public_id": "E-43c337fb7f5e535e",
          "rated_matches": 46,
          "raw_elo_rating": 1441.898196137617,
          "reasoning": "high",
          "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": 38.24445504127137,
          "uncertainty": 29.182495748947275,
          "unilateral_faults": 0,
          "wins": 17
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 44,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 22,
          "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-03T15:45:00Z",
          "losses": 28,
          "model": "o3",
          "point_rating_method": "sequential_elo",
          "public_id": "E-541cee4461c65fcb",
          "rated_matches": 44,
          "raw_elo_rating": 1400.2873857932564,
          "reasoning": "high",
          "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": 33.97300127592274,
          "uncertainty": 30.785599249992988,
          "unilateral_faults": 0,
          "wins": 16
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 50,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 25,
          "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
            "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": 25,
          "model": "o3",
          "point_rating_method": "sequential_elo",
          "public_id": "E-585aa996c86c4b8a",
          "rated_matches": 50,
          "raw_elo_rating": 1495.7553944062338,
          "reasoning": "low",
          "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": 43.84023648176475,
          "uncertainty": 26.264004201400486,
          "unilateral_faults": 0,
          "wins": 25
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 46,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 23,
          "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 26,
          "model": "o3",
          "point_rating_method": "sequential_elo",
          "public_id": "E-bc20ac8102f6a0ac",
          "rated_matches": 46,
          "raw_elo_rating": 1488.5445965948081,
          "reasoning": "high",
          "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": 42.889655450537184,
          "uncertainty": 29.182495748947275,
          "unilateral_faults": 0,
          "wins": 20
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 50,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 25,
          "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": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-03T16:00:00Z",
          "losses": 40,
          "model": "o3",
          "point_rating_method": "sequential_elo",
          "public_id": "E-ee95d01578313864",
          "rated_matches": 50,
          "raw_elo_rating": 1313.573763760422,
          "reasoning": "high",
          "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": 25.697996631697677,
          "uncertainty": 26.264004201400486,
          "unilateral_faults": 0,
          "wins": 10
        },
        {
          "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": "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": 102,
          "raw_elo_rating": 1624.3448206991122,
          "reasoning": "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": 58.2984762422112,
          "uncertainty": 5.516463908214657,
          "unilateral_faults": 0,
          "wins": 60
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 50,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 25,
          "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": 39,
          "model": "openai/gpt-oss-120b",
          "point_rating_method": "sequential_elo",
          "public_id": "E-29bc7f4fdf0f7b14",
          "rated_matches": 50,
          "raw_elo_rating": 1310.7089917355493,
          "reasoning": "high",
          "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": 25.412713307540546,
          "uncertainty": 26.264004201400486,
          "unilateral_faults": 0,
          "wins": 11
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 48,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 24,
          "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": 35,
          "model": "openai/gpt-oss-120b",
          "point_rating_method": "sequential_elo",
          "public_id": "E-759d747bb732d949",
          "rated_matches": 48,
          "raw_elo_rating": 1294.4125387163276,
          "reasoning": "low",
          "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": 23.677165697198408,
          "uncertainty": 27.678571428571434,
          "unilateral_faults": 0,
          "wins": 13
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 105,
          "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": 59,
          "model": "poolside/laguna-s-2.1",
          "point_rating_method": "sequential_elo",
          "public_id": "E-069a963abdd14cdf",
          "rated_matches": 96,
          "raw_elo_rating": 1482.0506801872393,
          "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": 44.008795335771325,
          "uncertainty": 7.017308256680951,
          "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": "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-d8e68d23876f6d21",
          "rated_matches": 98,
          "raw_elo_rating": 1614.907125088047,
          "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": 57.280134178672675,
          "uncertainty": 6.501890762960602,
          "unilateral_faults": 0,
          "wins": 51
        },
        {
          "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": 1705.0967292013736,
          "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": 66.08924139036272,
          "uncertainty": 8.664241836095918,
          "unilateral_faults": 0,
          "wins": 58
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 58,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 29,
          "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": 8,
          "model": "qwen/qwen3.7-max",
          "point_rating_method": "sequential_elo",
          "public_id": "E-59c7745eb1e91d63",
          "rated_matches": 58,
          "raw_elo_rating": 1774.854267128815,
          "reasoning": "enabled",
          "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": 72.02573454075652,
          "uncertainty": 21.344455490411935,
          "unilateral_faults": 0,
          "wins": 50
        },
        {
          "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": 1131.5762374150424,
          "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": 8.83134021951195,
          "uncertainty": 10.482614454664043,
          "unilateral_faults": 2,
          "wins": 18
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 68,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 34,
          "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": 40,
          "model": "qwen/qwen3.7-plus",
          "point_rating_method": "sequential_elo",
          "public_id": "E-9d091700cb41ece2",
          "rated_matches": 68,
          "raw_elo_rating": 1401.450531065138,
          "reasoning": "enabled",
          "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": 35.231463099790034,
          "uncertainty": 16.4429265428846,
          "unilateral_faults": 0,
          "wins": 28
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 58,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 29,
          "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": 31,
          "model": "stepfun/step-3.7-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-1140a7c92290e8f4",
          "rated_matches": 58,
          "raw_elo_rating": 1394.0233627026678,
          "reasoning": "low",
          "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": 34.10135332885759,
          "uncertainty": 21.344455490411935,
          "unilateral_faults": 0,
          "wins": 27
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 53,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 27,
          "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": 43,
          "model": "stepfun/step-3.7-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-6a5e44fe2dde4257",
          "rated_matches": 53,
          "raw_elo_rating": 1261.8941078649368,
          "reasoning": "high",
          "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": 20.708720393485684,
          "uncertainty": 24.291381743977166,
          "unilateral_faults": 0,
          "wins": 10
        },
        {
          "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": "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": 44,
          "model": "tencent/hy3-preview",
          "point_rating_method": "sequential_elo",
          "public_id": "E-dfed1e345a939bcd",
          "rated_matches": 52,
          "raw_elo_rating": 1237.7335607826108,
          "reasoning": "high",
          "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": 18.25183545143426,
          "uncertainty": 24.930281974344517,
          "unilateral_faults": 0,
          "wins": 8
        },
        {
          "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": 1364.5064243167951,
          "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": 32.460482495895945,
          "uncertainty": 5.045003647426665,
          "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": "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": 44,
          "model": "thinkingmachines/inkling",
          "point_rating_method": "sequential_elo",
          "public_id": "E-38e756fc6f3a2db6",
          "rated_matches": 52,
          "raw_elo_rating": 1260.0528626269393,
          "reasoning": "max",
          "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": 20.47446418689157,
          "uncertainty": 24.930281974344517,
          "unilateral_faults": 0,
          "wins": 8
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 68,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 34,
          "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": 58,
          "model": "thinkingmachines/inkling",
          "point_rating_method": "sequential_elo",
          "public_id": "E-b9ceec0ad4a1b9a4",
          "rated_matches": 68,
          "raw_elo_rating": 1196.149393725581,
          "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": 14.786907510390217,
          "uncertainty": 16.4429265428846,
          "unilateral_faults": 0,
          "wins": 10
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 36,
          "capped_draws": 0,
          "coverage_status": "under_covered",
          "distinct_rated_opponents": 18,
          "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": 8,
          "model": "x-ai/grok-4.5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-1d206565b78f3121",
          "rated_matches": 36,
          "raw_elo_rating": 1739.8022649892123,
          "reasoning": "low",
          "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": 67.17244175325133,
          "uncertainty": 38.449493652678655,
          "unilateral_faults": 0,
          "wins": 28
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 44,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 22,
          "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": 18,
          "model": "x-ai/grok-4.5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-436a3933a93e10cd",
          "rated_matches": 44,
          "raw_elo_rating": 1628.7660671784279,
          "reasoning": "high",
          "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": 56.72565215308805,
          "uncertainty": 30.785599249992988,
          "unilateral_faults": 0,
          "wins": 26
        },
        {
          "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": 1630.4735516007104,
          "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": 59.08648524326837,
          "uncertainty": 3.286043419179858,
          "unilateral_faults": 0,
          "wins": 65
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 64,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 32,
          "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": 55,
          "model": "x-ai/grok-build-0.1",
          "point_rating_method": "sequential_elo",
          "public_id": "E-37ae0129627ee16f",
          "rated_matches": 64,
          "raw_elo_rating": 1198.4872693708057,
          "reasoning": "enabled",
          "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": 14.874373778371579,
          "uncertainty": 18.26736729460423,
          "unilateral_faults": 0,
          "wins": 9
        },
        {
          "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": 1216.326014794011,
          "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": 17.320948925619717,
          "uncertainty": 9.855626741889738,
          "unilateral_faults": 2,
          "wins": 27
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 56,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 28,
          "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": 29,
          "model": "xiaomi/mimo-v2.5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-345a5b25cbac7f3b",
          "rated_matches": 56,
          "raw_elo_rating": 1512.3181251054739,
          "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": 45.79133533231307,
          "uncertainty": 22.47661785325219,
          "unilateral_faults": 0,
          "wins": 27
        },
        {
          "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": 38,
          "model": "xiaomi/mimo-v2.5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-47d67dcf0077af42",
          "rated_matches": 86,
          "raw_elo_rating": 1553.7177285588737,
          "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": 50.91951412041442,
          "uncertainty": 9.855626741889738,
          "unilateral_faults": 0,
          "wins": 48
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 66,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 33,
          "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": 43,
          "model": "xiaomi/mimo-v2.5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-fa1a93f7e4d57000",
          "rated_matches": 66,
          "raw_elo_rating": 1368.7633346415093,
          "reasoning": "enabled",
          "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": 31.905319340699265,
          "uncertainty": 17.33472217815261,
          "unilateral_faults": 0,
          "wins": 23
        },
        {
          "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": "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": 39,
          "model": "xiaomi/mimo-v2.5-pro",
          "point_rating_method": "sequential_elo",
          "public_id": "E-3b160130ae038271",
          "rated_matches": 78,
          "raw_elo_rating": 1568.0220467900822,
          "reasoning": "enabled",
          "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": 52.13296631946379,
          "uncertainty": 12.5043950463012,
          "unilateral_faults": 0,
          "wins": 39
        },
        {
          "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": "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": 36,
          "model": "xiaomi/mimo-v2.5-pro",
          "point_rating_method": "sequential_elo",
          "public_id": "E-83580d03385c6759",
          "rated_matches": 92,
          "raw_elo_rating": 1554.93981257272,
          "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": 51.181270461651444,
          "uncertainty": 8.09758473652126,
          "unilateral_faults": 0,
          "wins": 56
        },
        {
          "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": "2026-07-11T14:00:45Z",
          "losses": 41,
          "model": "z-ai/glm-5.2",
          "point_rating_method": "sequential_elo",
          "public_id": "E-62e8714f035ebc68",
          "rated_matches": 70,
          "raw_elo_rating": 1428.1721734848647,
          "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": 37.960514063897726,
          "uncertainty": 15.58908290969266,
          "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": "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": 38,
          "model": "z-ai/glm-5.2",
          "point_rating_method": "sequential_elo",
          "public_id": "E-e31f275ab7ef3741",
          "rated_matches": 76,
          "raw_elo_rating": 1632.9069856979993,
          "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": 58.53659031600019,
          "uncertainty": 13.230288229818967,
          "unilateral_faults": 0,
          "wins": 38
        },
        {
          "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": "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": 32,
          "model": "z-ai/glm-5.2",
          "point_rating_method": "sequential_elo",
          "public_id": "E-ecd98326faa92bf4",
          "rated_matches": 78,
          "raw_elo_rating": 1545.2260932564172,
          "reasoning": "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": 49.862871057100186,
          "uncertainty": 12.5043950463012,
          "unilateral_faults": 0,
          "wins": 46
        }
      ],
      "GB2-08": [
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 100,
          "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": 100,
          "raw_elo_rating": 2047.0897119000806,
          "reasoning": "xhigh",
          "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": 6.001859510499461,
          "unilateral_faults": 0,
          "wins": 95
        },
        {
          "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": "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": 1814.5336004592846,
          "reasoning": "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": 72.22544650832927,
          "uncertainty": 8.09758473652126,
          "unilateral_faults": 0,
          "wins": 80
        },
        {
          "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": "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": 88,
          "raw_elo_rating": 1781.1633732381583,
          "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": 68.15920342920347,
          "uncertainty": 9.249894000318006,
          "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": "legacy_shared_thinking_budget",
          "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": "legacy_shared_thinking_budget",
          "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": 84,
          "capped_draws": 1,
          "coverage_status": "rated",
          "distinct_rated_opponents": 42,
          "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-4-5",
            "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": 17,
          "model": "claude-opus-4-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-72233463ddce5549",
          "rated_matches": 84,
          "raw_elo_rating": 1789.2666943887314,
          "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": 69.00313139343699,
          "uncertainty": 10.482614454664043,
          "unilateral_faults": 0,
          "wins": 66
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 50,
          "capped_draws": 24,
          "coverage_status": "rated",
          "distinct_rated_opponents": 25,
          "draws": 24,
          "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": 20,
          "model": "claude-opus-4-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-877eec51affacb3a",
          "rated_matches": 50,
          "raw_elo_rating": 1422.5591374636776,
          "reasoning": "high",
          "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": 24.02309284446473,
          "uncertainty": 26.264004201400486,
          "unilateral_faults": 0,
          "wins": 6
        },
        {
          "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": "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": 96,
          "raw_elo_rating": 1769.8005525842925,
          "reasoning": "xhigh",
          "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": 67.02362320555288,
          "uncertainty": 7.017308256680951,
          "unilateral_faults": 0,
          "wins": 73
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 108,
          "capped_draws": 82,
          "coverage_status": "rated",
          "distinct_rated_opponents": 54,
          "draws": 82,
          "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": 108,
          "raw_elo_rating": 1422.9709089457906,
          "reasoning": "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": 26.170508876258452,
          "uncertainty": 4.1413142610575715,
          "unilateral_faults": 0,
          "wins": 5
        },
        {
          "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": "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": 88,
          "raw_elo_rating": 1767.4200337972638,
          "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": 66.52956277651462,
          "uncertainty": 9.249894000318006,
          "unilateral_faults": 0,
          "wins": 63
        },
        {
          "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": "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": 100,
          "raw_elo_rating": 1846.6915020635672,
          "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": 76.23742971057715,
          "uncertainty": 6.001859510499461,
          "unilateral_faults": 0,
          "wins": 80
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 70,
          "capped_draws": 7,
          "coverage_status": "rated",
          "distinct_rated_opponents": 35,
          "draws": 7,
          "evaluated_setting_identity": {
            "canonical_provider_route": "anthropic",
            "effective_request_value": "none",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "claude-opus-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-43cc1c89fa5720b3",
          "rated_matches": 70,
          "raw_elo_rating": 1764.9276140971756,
          "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": 65.63267534378616,
          "uncertainty": 15.58908290969266,
          "unilateral_faults": 0,
          "wins": 51
        },
        {
          "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": "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": 36,
          "model": "claude-opus-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-5a7942274854aaa6",
          "rated_matches": 112,
          "raw_elo_rating": 1636.5767116211482,
          "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": 51.580324918294124,
          "uncertainty": 3.286043419179858,
          "unilateral_faults": 0,
          "wins": 76
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 84,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 38,
          "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": 84,
          "raw_elo_rating": 1865.096194166436,
          "reasoning": "xhigh",
          "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": 77.99474773546663,
          "uncertainty": 10.482614454664043,
          "unilateral_faults": 0,
          "wins": 71
        },
        {
          "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": 8,
          "model": "claude-opus-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-e73b6fb78880341d",
          "rated_matches": 102,
          "raw_elo_rating": 1957.514655189079,
          "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": 89.4245253722117,
          "uncertainty": 5.516463908214657,
          "unilateral_faults": 0,
          "wins": 94
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 86,
          "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": 86,
          "raw_elo_rating": 1687.0626479500045,
          "reasoning": "xhigh",
          "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": 56.9435837175424,
          "uncertainty": 9.855626741889738,
          "unilateral_faults": 0,
          "wins": 60
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 110,
          "capped_draws": 83,
          "coverage_status": "rated",
          "distinct_rated_opponents": 55,
          "draws": 83,
          "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": 110,
          "raw_elo_rating": 1426.2683033126514,
          "reasoning": "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": 26.602617521323882,
          "uncertainty": 3.707899787624953,
          "unilateral_faults": 0,
          "wins": 7
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 118,
          "capped_draws": 94,
          "coverage_status": "rated",
          "distinct_rated_opponents": 52,
          "draws": 94,
          "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": 118,
          "raw_elo_rating": 1422.2229879671406,
          "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": 26.27689482403025,
          "uncertainty": 2.084924851410568,
          "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": 1392.708579434299,
          "reasoning": "enabled",
          "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": 21.41515165958451,
          "uncertainty": 16.4429265428846,
          "unilateral_faults": 0,
          "wins": 0
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 110,
          "capped_draws": 86,
          "coverage_status": "rated",
          "distinct_rated_opponents": 53,
          "draws": 86,
          "evaluated_setting_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": 110,
          "raw_elo_rating": 1424.5465939205094,
          "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": 26.3984628011689,
          "uncertainty": 3.707899787624953,
          "unilateral_faults": 0,
          "wins": 6
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 78,
          "capped_draws": 69,
          "coverage_status": "rated",
          "distinct_rated_opponents": 39,
          "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": "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": 78,
          "raw_elo_rating": 1444.6969290589077,
          "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": 27.953376319747385,
          "uncertainty": 12.5043950463012,
          "unilateral_faults": 0,
          "wins": 2
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 104,
          "capped_draws": 73,
          "coverage_status": "rated",
          "distinct_rated_opponents": 52,
          "draws": 73,
          "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": 104,
          "raw_elo_rating": 1410.422225981586,
          "reasoning": "xhigh",
          "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": 24.5968014699668,
          "uncertainty": 5.045003647426665,
          "unilateral_faults": 0,
          "wins": 2
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 82,
          "capped_draws": 71,
          "coverage_status": "rated",
          "distinct_rated_opponents": 41,
          "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": "2026-07-01T00:15:48Z",
          "losses": 9,
          "model": "deepseek/deepseek-v4-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-d28ef17ff6995c62",
          "rated_matches": 82,
          "raw_elo_rating": 1410.6372546204118,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "repaired",
          "score": 24.04486549659256,
          "uncertainty": 11.132129994845172,
          "unilateral_faults": 0,
          "wins": 2
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 88,
          "capped_draws": 59,
          "coverage_status": "rated",
          "distinct_rated_opponents": 43,
          "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-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": 88,
          "raw_elo_rating": 1405.469355363088,
          "reasoning": "xhigh",
          "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": 23.61062430589122,
          "uncertainty": 9.249894000318006,
          "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": 1525.8670668329498,
          "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": 38.37160182164898,
          "uncertainty": 4.1413142610575715,
          "unilateral_faults": 0,
          "wins": 9
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 54,
          "capped_draws": 27,
          "coverage_status": "rated",
          "distinct_rated_opponents": 27,
          "draws": 27,
          "evaluated_setting_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": 25,
          "model": "google/gemini-3.1-flash-lite",
          "point_rating_method": "sequential_elo",
          "public_id": "E-b335c9f92035f80b",
          "rated_matches": 54,
          "raw_elo_rating": 1352.224951324873,
          "reasoning": "high",
          "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": 15.929165179121178,
          "uncertainty": 23.66998624632421,
          "unilateral_faults": 0,
          "wins": 2
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 130,
          "capped_draws": 40,
          "coverage_status": "rated",
          "distinct_rated_opponents": 65,
          "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": 130,
          "raw_elo_rating": 1436.5502098452275,
          "reasoning": "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": 28.179696020170926,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 39
        },
        {
          "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": "low",
          "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": 67,
          "coverage_status": "rated",
          "distinct_rated_opponents": 44,
          "draws": 67,
          "evaluated_setting_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": 21,
          "model": "google/gemini-3.5-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-bd0bbefbbd252fc5",
          "rated_matches": 88,
          "raw_elo_rating": 1368.2923757001072,
          "reasoning": "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": 19.20229853735902,
          "uncertainty": 9.249894000318006,
          "unilateral_faults": 0,
          "wins": 0
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 54,
          "capped_draws": 26,
          "coverage_status": "rated",
          "distinct_rated_opponents": 27,
          "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": "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": 28,
          "model": "google/gemini-3.5-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-fa332e578ae97122",
          "rated_matches": 54,
          "raw_elo_rating": 1302.1407704231513,
          "reasoning": "high",
          "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": 9.990345316227936,
          "uncertainty": 23.66998624632421,
          "unilateral_faults": 0,
          "wins": 0
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 36,
          "capped_draws": 31,
          "coverage_status": "under_covered",
          "distinct_rated_opponents": 18,
          "draws": 31,
          "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": 4,
          "model": "google/gemini-3.5-flash-lite",
          "point_rating_method": "sequential_elo",
          "public_id": "E-284d554eca16e6f6",
          "rated_matches": 36,
          "raw_elo_rating": 1453.3075258165225,
          "reasoning": "minimal",
          "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": 26.513204409086146,
          "uncertainty": 38.449493652678655,
          "unilateral_faults": 0,
          "wins": 1
        },
        {
          "admitted_plugin_count": 2,
          "attempted_matches": 52,
          "capped_draws": 28,
          "coverage_status": "rated",
          "distinct_rated_opponents": 26,
          "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": 23,
          "model": "google/gemini-3.5-flash-lite",
          "point_rating_method": "sequential_elo",
          "public_id": "E-2a14d2f80ade1bda",
          "rated_matches": 52,
          "raw_elo_rating": 1351.1408038338798,
          "reasoning": "high",
          "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": 15.681057056511584,
          "uncertainty": 24.930281974344517,
          "unilateral_faults": 0,
          "wins": 1
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 76,
          "capped_draws": 62,
          "coverage_status": "rated",
          "distinct_rated_opponents": 38,
          "draws": 62,
          "evaluated_setting_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": 11,
          "model": "google/gemini-3.5-flash-lite",
          "point_rating_method": "sequential_elo",
          "public_id": "E-2f2aa5b1beafd6e6",
          "rated_matches": 76,
          "raw_elo_rating": 1431.6257184265396,
          "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": 26.334575273965037,
          "uncertainty": 13.230288229818967,
          "unilateral_faults": 0,
          "wins": 3
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 68,
          "capped_draws": 54,
          "coverage_status": "rated",
          "distinct_rated_opponents": 34,
          "draws": 54,
          "evaluated_setting_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": 12,
          "model": "google/gemini-3.5-flash-lite",
          "point_rating_method": "sequential_elo",
          "public_id": "E-9b50de854a87d3c6",
          "rated_matches": 68,
          "raw_elo_rating": 1427.9398227851348,
          "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": 25.59275832179461,
          "uncertainty": 16.4429265428846,
          "unilateral_faults": 0,
          "wins": 2
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 38,
          "capped_draws": 33,
          "coverage_status": "under_covered",
          "distinct_rated_opponents": 19,
          "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-3.5-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": 4,
          "model": "google/gemini-3.5-flash-lite",
          "point_rating_method": "sequential_elo",
          "public_id": "E-af119b49b8f1d63d",
          "rated_matches": 38,
          "raw_elo_rating": 1455.3639544861342,
          "reasoning": "minimal",
          "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": 26.95961769480189,
          "uncertainty": 36.31407690254356,
          "unilateral_faults": 0,
          "wins": 1
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 52,
          "capped_draws": 8,
          "coverage_status": "rated",
          "distinct_rated_opponents": 26,
          "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": "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-620b5ca2bcd82419",
          "rated_matches": 52,
          "raw_elo_rating": 1676.6846736132431,
          "reasoning": "high",
          "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": 54.28299414084854,
          "uncertainty": 24.930281974344517,
          "unilateral_faults": 0,
          "wins": 34
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 38,
          "capped_draws": 33,
          "coverage_status": "under_covered",
          "distinct_rated_opponents": 19,
          "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": 4,
          "model": "google/gemini-3.6-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-657c523bc9e9f80c",
          "rated_matches": 38,
          "raw_elo_rating": 1451.0945398206582,
          "reasoning": "minimal",
          "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": 26.45336433971537,
          "uncertainty": 36.31407690254356,
          "unilateral_faults": 0,
          "wins": 1
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 56,
          "capped_draws": 9,
          "coverage_status": "rated",
          "distinct_rated_opponents": 28,
          "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": "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": 17,
          "model": "google/gemini-3.6-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-ab7ee826f8050f04",
          "rated_matches": 56,
          "raw_elo_rating": 1654.1866708150255,
          "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": 51.848011910482846,
          "uncertainty": 22.47661785325219,
          "unilateral_faults": 0,
          "wins": 30
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 44,
          "capped_draws": 37,
          "coverage_status": "rated",
          "distinct_rated_opponents": 22,
          "draws": 37,
          "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": 6,
          "model": "google/gemini-3.6-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-c694a36a5e4e3f09",
          "rated_matches": 44,
          "raw_elo_rating": 1432.0809863594432,
          "reasoning": "minimal",
          "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": 24.723237958811644,
          "uncertainty": 30.785599249992988,
          "unilateral_faults": 0,
          "wins": 1
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 46,
          "capped_draws": 23,
          "coverage_status": "rated",
          "distinct_rated_opponents": 23,
          "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-3.6-flash",
            "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 20,
          "model": "google/gemini-3.6-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-efad9f3f4e9183a0",
          "rated_matches": 46,
          "raw_elo_rating": 1379.2854789302758,
          "reasoning": "high",
          "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": 18.614990437288874,
          "uncertainty": 29.182495748947275,
          "unilateral_faults": 0,
          "wins": 3
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 116,
          "capped_draws": 92,
          "coverage_status": "rated",
          "distinct_rated_opponents": 56,
          "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": "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": 116,
          "raw_elo_rating": 1436.356567823582,
          "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": 27.91580429175553,
          "uncertainty": 2.4750163521024238,
          "unilateral_faults": 0,
          "wins": 3
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 106,
          "capped_draws": 79,
          "coverage_status": "rated",
          "distinct_rated_opponents": 50,
          "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": 106,
          "raw_elo_rating": 1415.6268161240855,
          "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": 25.257408425790306,
          "uncertainty": 4.586824452283178,
          "unilateral_faults": 0,
          "wins": 11
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 88,
          "capped_draws": 54,
          "coverage_status": "rated",
          "distinct_rated_opponents": 44,
          "draws": 54,
          "evaluated_setting_identity": {
            "canonical_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": 88,
          "raw_elo_rating": 1387.3551553183834,
          "reasoning": "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": 21.462701167505323,
          "uncertainty": 9.249894000318006,
          "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": "low",
          "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": 54,
          "capped_draws": 25,
          "coverage_status": "rated",
          "distinct_rated_opponents": 27,
          "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": "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": 23,
          "model": "gpt-5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-ebca8ea756b4a4ad",
          "rated_matches": 54,
          "raw_elo_rating": 1381.3649590509233,
          "reasoning": "high",
          "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": 19.384492860887867,
          "uncertainty": 23.66998624632421,
          "unilateral_faults": 0,
          "wins": 6
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 104,
          "capped_draws": 72,
          "coverage_status": "rated",
          "distinct_rated_opponents": 51,
          "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-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": 104,
          "raw_elo_rating": 1450.841570816661,
          "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": 29.38959639303247,
          "uncertainty": 5.045003647426665,
          "unilateral_faults": 0,
          "wins": 12
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 100,
          "capped_draws": 38,
          "coverage_status": "rated",
          "distinct_rated_opponents": 50,
          "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": 31,
          "model": "gpt-5.4",
          "point_rating_method": "sequential_elo",
          "public_id": "E-b13a2be40d59c1ea",
          "rated_matches": 100,
          "raw_elo_rating": 1459.2219261759235,
          "reasoning": "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": 30.292543079332418,
          "uncertainty": 6.001859510499461,
          "unilateral_faults": 0,
          "wins": 31
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 100,
          "capped_draws": 26,
          "coverage_status": "rated",
          "distinct_rated_opponents": 47,
          "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": 100,
          "raw_elo_rating": 1602.560257343934,
          "reasoning": "xhigh",
          "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": 47.28913787090833,
          "uncertainty": 6.001859510499461,
          "unilateral_faults": 0,
          "wins": 43
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 114,
          "capped_draws": 41,
          "coverage_status": "rated",
          "distinct_rated_opponents": 57,
          "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": 1436.6611574632266,
          "reasoning": "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": 27.91395572652641,
          "uncertainty": 2.875240412015687,
          "unilateral_faults": 0,
          "wins": 35
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 88,
          "capped_draws": 74,
          "coverage_status": "rated",
          "distinct_rated_opponents": 43,
          "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-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": 12,
          "model": "gpt-5.4-mini",
          "point_rating_method": "sequential_elo",
          "public_id": "E-bb8ac98c284a38ce",
          "rated_matches": 86,
          "raw_elo_rating": 1439.4052725343836,
          "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": 27.577174727119328,
          "uncertainty": 9.855626741889738,
          "unilateral_faults": 2,
          "wins": 0
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 106,
          "capped_draws": 89,
          "coverage_status": "rated",
          "distinct_rated_opponents": 52,
          "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-5.4-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": 106,
          "raw_elo_rating": 1411.3491671939846,
          "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": 24.750178678289455,
          "uncertainty": 4.586824452283178,
          "unilateral_faults": 0,
          "wins": 0
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 94,
          "capped_draws": 52,
          "coverage_status": "rated",
          "distinct_rated_opponents": 47,
          "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": 1367.8675099857733,
          "reasoning": "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": 19.313276352756375,
          "uncertainty": 7.54891760425771,
          "unilateral_faults": 0,
          "wins": 5
        },
        {
          "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": "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": 1853.1383592528794,
          "reasoning": "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": 76.85512103552502,
          "uncertainty": 7.54891760425771,
          "unilateral_faults": 0,
          "wins": 72
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 86,
          "capped_draws": 4,
          "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-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": 86,
          "raw_elo_rating": 1660.009150077097,
          "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": 53.73566761238275,
          "uncertainty": 9.855626741889738,
          "unilateral_faults": 0,
          "wins": 54
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 112,
          "capped_draws": 50,
          "coverage_status": "rated",
          "distinct_rated_opponents": 56,
          "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": 1605.807541988619,
          "reasoning": "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": 47.93181649730258,
          "uncertainty": 3.286043419179858,
          "unilateral_faults": 0,
          "wins": 38
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 102,
          "capped_draws": 16,
          "coverage_status": "rated",
          "distinct_rated_opponents": 46,
          "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": 102,
          "raw_elo_rating": 1783.5389156654253,
          "reasoning": "xhigh",
          "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": 68.79504598485697,
          "uncertainty": 5.516463908214657,
          "unilateral_faults": 0,
          "wins": 62
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 104,
          "capped_draws": 81,
          "coverage_status": "rated",
          "distinct_rated_opponents": 50,
          "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-5.5",
            "reasoning_catalog_sha256": "unknown_legacy",
            "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_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": 104,
          "raw_elo_rating": 1439.4705060316537,
          "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": 28.041252381178502,
          "uncertainty": 5.045003647426665,
          "unilateral_faults": 0,
          "wins": 4
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 92,
          "capped_draws": 6,
          "coverage_status": "rated",
          "distinct_rated_opponents": 45,
          "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-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": 92,
          "raw_elo_rating": 1645.1650048305432,
          "reasoning": "xhigh",
          "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": 52.14226731360425,
          "uncertainty": 8.09758473652126,
          "unilateral_faults": 0,
          "wins": 55
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 106,
          "capped_draws": 87,
          "coverage_status": "rated",
          "distinct_rated_opponents": 52,
          "draws": 87,
          "evaluated_setting_identity": {
            "canonical_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": 106,
          "raw_elo_rating": 1435.4850403755702,
          "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": 27.612132302735073,
          "uncertainty": 4.586824452283178,
          "unilateral_faults": 0,
          "wins": 1
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 112,
          "capped_draws": 87,
          "coverage_status": "rated",
          "distinct_rated_opponents": 56,
          "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": 18,
          "model": "gpt-5.6-luna",
          "point_rating_method": "sequential_elo",
          "public_id": "E-e6198d88365e0492",
          "rated_matches": 112,
          "raw_elo_rating": 1429.4023399340574,
          "reasoning": "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": 27.014259316222454,
          "uncertainty": 3.286043419179858,
          "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": 1778.443049602078,
          "reasoning": "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": 67.83663626822397,
          "uncertainty": 9.249894000318006,
          "unilateral_faults": 0,
          "wins": 64
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 84,
          "capped_draws": 12,
          "coverage_status": "rated",
          "distinct_rated_opponents": 42,
          "draws": 12,
          "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": 50,
          "model": "gpt-5.6-sol",
          "point_rating_method": "sequential_elo",
          "public_id": "E-3ae62f195160add3",
          "rated_matches": 84,
          "raw_elo_rating": 1378.8902558829477,
          "reasoning": "xhigh",
          "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": 20.34202322749009,
          "uncertainty": 10.482614454664043,
          "unilateral_faults": 0,
          "wins": 22
        },
        {
          "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": 1539.1028287524625,
          "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": 39.5657581912891,
          "uncertainty": 8.09758473652126,
          "unilateral_faults": 0,
          "wins": 43
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 100,
          "capped_draws": 72,
          "coverage_status": "rated",
          "distinct_rated_opponents": 49,
          "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-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": 98,
          "raw_elo_rating": 1411.6697828592557,
          "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": 24.606530359301495,
          "uncertainty": 6.501890762960602,
          "unilateral_faults": 2,
          "wins": 3
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 98,
          "capped_draws": 15,
          "coverage_status": "rated",
          "distinct_rated_opponents": 46,
          "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": 32,
          "model": "gpt-5.6-terra",
          "point_rating_method": "sequential_elo",
          "public_id": "E-b061663dc342c859",
          "rated_matches": 98,
          "raw_elo_rating": 1615.127256233949,
          "reasoning": "xhigh",
          "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": 48.731858204888034,
          "uncertainty": 6.501890762960602,
          "unilateral_faults": 0,
          "wins": 51
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 108,
          "capped_draws": 53,
          "coverage_status": "rated",
          "distinct_rated_opponents": 54,
          "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": 1485.5625871021477,
          "reasoning": "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": 33.5924272304032,
          "uncertainty": 4.1413142610575715,
          "unilateral_faults": 0,
          "wins": 21
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 156,
          "capped_draws": 136,
          "coverage_status": "rated",
          "distinct_rated_opponents": 59,
          "draws": 136,
          "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": 152,
          "raw_elo_rating": 1434.8991121674007,
          "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": 28.293408909065196,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 0
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 152,
          "capped_draws": 126,
          "coverage_status": "rated",
          "distinct_rated_opponents": 63,
          "draws": 126,
          "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": 152,
          "raw_elo_rating": 1408.9913624159817,
          "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": 25.221351903111337,
          "uncertainty": 0.0,
          "unilateral_faults": 0,
          "wins": 5
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 110,
          "capped_draws": 99,
          "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": "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": 110,
          "raw_elo_rating": 1434.148802550992,
          "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": 27.537061582573646,
          "uncertainty": 3.707899787624953,
          "unilateral_faults": 0,
          "wins": 1
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 42,
          "capped_draws": 17,
          "coverage_status": "rated",
          "distinct_rated_opponents": 21,
          "draws": 17,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "enabled",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "meituan/longcat-2.0",
            "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 24,
          "model": "meituan/longcat-2.0",
          "point_rating_method": "sequential_elo",
          "public_id": "E-d724da56cbc06da7",
          "rated_matches": 42,
          "raw_elo_rating": 1315.9608699542914,
          "reasoning": "enabled",
          "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": 10.791528209491693,
          "uncertainty": 32.49928516630233,
          "unilateral_faults": 0,
          "wins": 1
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 112,
          "capped_draws": 93,
          "coverage_status": "rated",
          "distinct_rated_opponents": 53,
          "draws": 93,
          "evaluated_setting_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": 112,
          "raw_elo_rating": 1439.5672369696829,
          "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": 28.219579865197666,
          "uncertainty": 3.286043419179858,
          "unilateral_faults": 0,
          "wins": 7
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 42,
          "capped_draws": 15,
          "coverage_status": "rated",
          "distinct_rated_opponents": 21,
          "draws": 15,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openrouter",
            "effective_request_value": "enabled",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "meituan/longcat-2.0",
            "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "toggle",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-24T13:40:00Z",
          "losses": 10,
          "model": "meituan/longcat-2.0",
          "point_rating_method": "sequential_elo",
          "public_id": "E-ef389910f6cc07cc",
          "rated_matches": 42,
          "raw_elo_rating": 1585.4966463069525,
          "reasoning": "enabled",
          "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": 42.75220708142079,
          "uncertainty": 32.49928516630233,
          "unilateral_faults": 0,
          "wins": 17
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 70,
          "capped_draws": 47,
          "coverage_status": "rated",
          "distinct_rated_opponents": 35,
          "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": "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": 16,
          "model": "minimax/minimax-m3",
          "point_rating_method": "sequential_elo",
          "public_id": "E-d169e7b29be70652",
          "rated_matches": 70,
          "raw_elo_rating": 1434.24782351636,
          "reasoning": "enabled",
          "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": 26.421737414855947,
          "uncertainty": 15.58908290969266,
          "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": 1523.101241228136,
          "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": 37.77081834649088,
          "uncertainty": 7.017308256680951,
          "unilateral_faults": 0,
          "wins": 40
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 114,
          "capped_draws": 90,
          "coverage_status": "rated",
          "distinct_rated_opponents": 57,
          "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": "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": 114,
          "raw_elo_rating": 1403.1981627791558,
          "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": 23.94602226083568,
          "uncertainty": 2.875240412015687,
          "unilateral_faults": 0,
          "wins": 2
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 60,
          "capped_draws": 4,
          "coverage_status": "rated",
          "distinct_rated_opponents": 30,
          "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": 11,
          "model": "moonshotai/kimi-k2.7-code",
          "point_rating_method": "sequential_elo",
          "public_id": "E-251b5d53a5f89562",
          "rated_matches": 60,
          "raw_elo_rating": 1723.2474480429453,
          "reasoning": "enabled",
          "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": 60.246485930241015,
          "uncertainty": 20.268439966447993,
          "unilateral_faults": 0,
          "wins": 45
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 62,
          "capped_draws": 43,
          "coverage_status": "rated",
          "distinct_rated_opponents": 31,
          "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": "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-151c4ee6a2d1838e",
          "rated_matches": 62,
          "raw_elo_rating": 1413.2261671604745,
          "reasoning": "high",
          "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": 23.582339471707066,
          "uncertainty": 19.244078834871203,
          "unilateral_faults": 0,
          "wins": 2
        },
        {
          "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": "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": 3,
          "model": "moonshotai/kimi-k3",
          "point_rating_method": "sequential_elo",
          "public_id": "E-3e1be56b9d966ded",
          "rated_matches": 52,
          "raw_elo_rating": 1817.7036945480477,
          "reasoning": "low",
          "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": 71.00457264118863,
          "uncertainty": 24.930281974344517,
          "unilateral_faults": 0,
          "wins": 49
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 108,
          "capped_draws": 94,
          "coverage_status": "rated",
          "distinct_rated_opponents": 53,
          "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": "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": 108,
          "raw_elo_rating": 1431.0354741384447,
          "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": 27.126778881865853,
          "uncertainty": 4.1413142610575715,
          "unilateral_faults": 0,
          "wins": 0
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 62,
          "capped_draws": 9,
          "coverage_status": "rated",
          "distinct_rated_opponents": 31,
          "draws": 9,
          "evaluated_setting_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": 49,
          "model": "nex-agi/nex-n2-pro",
          "point_rating_method": "sequential_elo",
          "public_id": "E-92332f4d765b2297",
          "rated_matches": 62,
          "raw_elo_rating": 1214.3479079348465,
          "reasoning": "enabled",
          "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": 19.244078834871203,
          "unilateral_faults": 0,
          "wins": 4
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 108,
          "capped_draws": 72,
          "coverage_status": "rated",
          "distinct_rated_opponents": 54,
          "draws": 72,
          "evaluated_setting_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": 108,
          "raw_elo_rating": 1440.809420939187,
          "reasoning": "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": 28.28574181894595,
          "uncertainty": 4.1413142610575715,
          "unilateral_faults": 0,
          "wins": 9
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 54,
          "capped_draws": 27,
          "coverage_status": "rated",
          "distinct_rated_opponents": 27,
          "draws": 27,
          "evaluated_setting_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": 23,
          "model": "nvidia/nemotron-3-ultra-550b-a55b",
          "point_rating_method": "sequential_elo",
          "public_id": "E-2e3c01d0103fc439",
          "rated_matches": 54,
          "raw_elo_rating": 1363.9872394644565,
          "reasoning": "high",
          "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": 17.323899188518354,
          "uncertainty": 23.66998624632421,
          "unilateral_faults": 0,
          "wins": 4
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 54,
          "capped_draws": 27,
          "coverage_status": "rated",
          "distinct_rated_opponents": 27,
          "draws": 27,
          "evaluated_setting_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": 54,
          "raw_elo_rating": 1362.0074927001401,
          "reasoning": "high",
          "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": 17.089147232995877,
          "uncertainty": 23.66998624632421,
          "unilateral_faults": 0,
          "wins": 4
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 82,
          "capped_draws": 76,
          "coverage_status": "rated",
          "distinct_rated_opponents": 41,
          "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": "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": 82,
          "raw_elo_rating": 1448.6728163873909,
          "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": 28.55499914859909,
          "uncertainty": 11.132129994845172,
          "unilateral_faults": 0,
          "wins": 1
        },
        {
          "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": "openai",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "o3",
            "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-03T16:00:00Z",
          "losses": 11,
          "model": "o3",
          "point_rating_method": "sequential_elo",
          "public_id": "E-2270b9df7d2b32cc",
          "rated_matches": 52,
          "raw_elo_rating": 1743.8525025680906,
          "reasoning": "high",
          "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": 62.247537626689,
          "uncertainty": 24.930281974344517,
          "unilateral_faults": 0,
          "wins": 41
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 48,
          "capped_draws": 43,
          "coverage_status": "rated",
          "distinct_rated_opponents": 24,
          "draws": 43,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "low",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "o3",
            "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-21T14:20:15Z",
          "losses": 4,
          "model": "o3",
          "point_rating_method": "sequential_elo",
          "public_id": "E-335ae90fdc702bd6",
          "rated_matches": 48,
          "raw_elo_rating": 1459.8687978096345,
          "reasoning": "low",
          "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": 28.31296362033054,
          "uncertainty": 27.678571428571434,
          "unilateral_faults": 0,
          "wins": 1
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 124,
          "capped_draws": 63,
          "coverage_status": "rated",
          "distinct_rated_opponents": 62,
          "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": 1466.4297670164335,
          "reasoning": "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": 31.624425793989726,
          "uncertainty": 0.9713595499957961,
          "unilateral_faults": 0,
          "wins": 29
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 52,
          "capped_draws": 29,
          "coverage_status": "rated",
          "distinct_rated_opponents": 26,
          "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": "o3",
            "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-03T15:45:00Z",
          "losses": 21,
          "model": "o3",
          "point_rating_method": "sequential_elo",
          "public_id": "E-9fbb8e6c69f575f4",
          "rated_matches": 52,
          "raw_elo_rating": 1344.1624701054743,
          "reasoning": "high",
          "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": 14.85358885777086,
          "uncertainty": 24.930281974344517,
          "unilateral_faults": 0,
          "wins": 2
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 52,
          "capped_draws": 27,
          "coverage_status": "rated",
          "distinct_rated_opponents": 26,
          "draws": 27,
          "evaluated_setting_identity": {
            "canonical_provider_route": "openai",
            "effective_request_value": "high",
            "output_mode": "unknown_legacy",
            "prompt_identity": "full_freedom",
            "prompt_profile_identity": "unknown_legacy",
            "provider_model": "o3",
            "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
            "reasoning_policy_version": "gb2_reasoning_brackets_v2",
            "request_mode": "effort",
            "resolution_status": "opaque_historical",
            "schema_version": "evaluated_setting_identity.v1"
          },
          "generated_at": "2026-07-02T16:51:45Z",
          "losses": 21,
          "model": "o3",
          "point_rating_method": "sequential_elo",
          "public_id": "E-afa6c09eebc859c4",
          "rated_matches": 52,
          "raw_elo_rating": 1383.3495651097662,
          "reasoning": "high",
          "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": 19.500267589269747,
          "uncertainty": 24.930281974344517,
          "unilateral_faults": 0,
          "wins": 4
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 54,
          "capped_draws": 29,
          "coverage_status": "rated",
          "distinct_rated_opponents": 27,
          "draws": 29,
          "evaluated_setting_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": 54,
          "raw_elo_rating": 1357.5269587677542,
          "reasoning": "high",
          "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": 16.55786003941604,
          "uncertainty": 23.66998624632421,
          "unilateral_faults": 0,
          "wins": 3
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 118,
          "capped_draws": 86,
          "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": "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": 1444.8116248114163,
          "reasoning": "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": 28.95538217774586,
          "uncertainty": 2.084924851410568,
          "unilateral_faults": 0,
          "wins": 9
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 52,
          "capped_draws": 32,
          "coverage_status": "rated",
          "distinct_rated_opponents": 26,
          "draws": 32,
          "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": 17,
          "model": "openai/gpt-oss-120b",
          "point_rating_method": "sequential_elo",
          "public_id": "E-f6e9da46c61ad315",
          "rated_matches": 52,
          "raw_elo_rating": 1389.000283498118,
          "reasoning": "low",
          "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": 20.170311463406588,
          "uncertainty": 24.930281974344517,
          "unilateral_faults": 0,
          "wins": 3
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 44,
          "capped_draws": 32,
          "coverage_status": "rated",
          "distinct_rated_opponents": 22,
          "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": "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": 9,
          "model": "poolside/laguna-s-2.1",
          "point_rating_method": "sequential_elo",
          "public_id": "E-0fab95afbec0dd98",
          "rated_matches": 44,
          "raw_elo_rating": 1439.6669918897676,
          "reasoning": "enabled",
          "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": 25.622761910534294,
          "uncertainty": 30.785599249992988,
          "unilateral_faults": 0,
          "wins": 3
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 112,
          "capped_draws": 96,
          "coverage_status": "rated",
          "distinct_rated_opponents": 53,
          "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": "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": 112,
          "raw_elo_rating": 1421.9028148300824,
          "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": 26.124989933198123,
          "uncertainty": 3.286043419179858,
          "unilateral_faults": 0,
          "wins": 3
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 112,
          "capped_draws": 93,
          "coverage_status": "rated",
          "distinct_rated_opponents": 53,
          "draws": 93,
          "evaluated_setting_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": 112,
          "raw_elo_rating": 1424.7782920481748,
          "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": 26.465954703124442,
          "uncertainty": 3.286043419179858,
          "unilateral_faults": 0,
          "wins": 3
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 44,
          "capped_draws": 35,
          "coverage_status": "rated",
          "distinct_rated_opponents": 22,
          "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": "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": 8,
          "model": "poolside/laguna-s-2.1",
          "point_rating_method": "sequential_elo",
          "public_id": "E-f72c72b8f264c57a",
          "rated_matches": 44,
          "raw_elo_rating": 1437.3867959450756,
          "reasoning": "enabled",
          "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": 25.352383664872303,
          "uncertainty": 30.785599249992988,
          "unilateral_faults": 0,
          "wins": 1
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 72,
          "capped_draws": 48,
          "coverage_status": "rated",
          "distinct_rated_opponents": 36,
          "draws": 48,
          "evaluated_setting_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": 19,
          "model": "qwen/qwen3.7-max",
          "point_rating_method": "sequential_elo",
          "public_id": "E-64624689e7cbd439",
          "rated_matches": 72,
          "raw_elo_rating": 1425.558769052083,
          "reasoning": "enabled",
          "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": 25.469062440505223,
          "uncertainty": 14.770573598065289,
          "unilateral_faults": 0,
          "wins": 5
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 108,
          "capped_draws": 74,
          "coverage_status": "rated",
          "distinct_rated_opponents": 53,
          "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": "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": 108,
          "raw_elo_rating": 1416.188024322118,
          "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": 25.366216398962596,
          "uncertainty": 4.1413142610575715,
          "unilateral_faults": 0,
          "wins": 4
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 76,
          "capped_draws": 58,
          "coverage_status": "rated",
          "distinct_rated_opponents": 38,
          "draws": 58,
          "evaluated_setting_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": 18,
          "model": "qwen/qwen3.7-plus",
          "point_rating_method": "sequential_elo",
          "public_id": "E-6c2a9942e92223c8",
          "rated_matches": 76,
          "raw_elo_rating": 1428.5564045306385,
          "reasoning": "enabled",
          "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": 25.970625978953073,
          "uncertainty": 13.230288229818967,
          "unilateral_faults": 0,
          "wins": 0
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 54,
          "capped_draws": 32,
          "coverage_status": "rated",
          "distinct_rated_opponents": 27,
          "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": "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": 54,
          "raw_elo_rating": 1364.6824009874317,
          "reasoning": "high",
          "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": 17.406329189094095,
          "uncertainty": 23.66998624632421,
          "unilateral_faults": 0,
          "wins": 1
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 52,
          "capped_draws": 37,
          "coverage_status": "rated",
          "distinct_rated_opponents": 26,
          "draws": 37,
          "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": 15,
          "model": "stepfun/step-3.7-flash",
          "point_rating_method": "sequential_elo",
          "public_id": "E-c38fe2712e69333b",
          "rated_matches": 52,
          "raw_elo_rating": 1382.0361210747858,
          "reasoning": "low",
          "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": 19.34452365209632,
          "uncertainty": 24.930281974344517,
          "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": "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": 112,
          "raw_elo_rating": 1436.4194727656443,
          "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": 27.84632818688169,
          "uncertainty": 3.286043419179858,
          "unilateral_faults": 0,
          "wins": 3
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 54,
          "capped_draws": 12,
          "coverage_status": "rated",
          "distinct_rated_opponents": 27,
          "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": "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": 24,
          "model": "tencent/hy3-preview",
          "point_rating_method": "sequential_elo",
          "public_id": "E-81a5e5ef15f371dc",
          "rated_matches": 54,
          "raw_elo_rating": 1457.1845022400166,
          "reasoning": "high",
          "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": 28.37492858290644,
          "uncertainty": 23.66998624632421,
          "unilateral_faults": 0,
          "wins": 18
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 112,
          "capped_draws": 7,
          "coverage_status": "rated",
          "distinct_rated_opponents": 54,
          "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": 112,
          "raw_elo_rating": 1735.2256601683764,
          "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": 63.27779754414018,
          "uncertainty": 3.286043419179858,
          "unilateral_faults": 0,
          "wins": 68
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 71,
          "capped_draws": 55,
          "coverage_status": "rated",
          "distinct_rated_opponents": 36,
          "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": "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": 12,
          "model": "thinkingmachines/inkling",
          "point_rating_method": "sequential_elo",
          "public_id": "E-9f74dab09049a473",
          "rated_matches": 71,
          "raw_elo_rating": 1442.2338469609456,
          "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": 27.407921076039756,
          "uncertainty": 15.175565098878963,
          "unilateral_faults": 0,
          "wins": 4
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 54,
          "capped_draws": 24,
          "coverage_status": "rated",
          "distinct_rated_opponents": 27,
          "draws": 24,
          "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": 28,
          "model": "thinkingmachines/inkling",
          "point_rating_method": "sequential_elo",
          "public_id": "E-d21921560d198b28",
          "rated_matches": 54,
          "raw_elo_rating": 1333.1838510286977,
          "reasoning": "max",
          "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": 13.67133321273315,
          "uncertainty": 23.66998624632421,
          "unilateral_faults": 0,
          "wins": 2
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 48,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 24,
          "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": 6,
          "model": "x-ai/grok-4.5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-707dd709e358a173",
          "rated_matches": 48,
          "raw_elo_rating": 1799.9643985417936,
          "reasoning": "high",
          "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": 68.64039780307307,
          "uncertainty": 27.678571428571434,
          "unilateral_faults": 0,
          "wins": 42
        },
        {
          "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": 1882.0961693922998,
          "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": 80.48164573606203,
          "uncertainty": 5.516463908214657,
          "unilateral_faults": 0,
          "wins": 87
        },
        {
          "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": "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": 8,
          "model": "x-ai/grok-4.5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-b914d026c7631fcb",
          "rated_matches": 52,
          "raw_elo_rating": 1773.667375508612,
          "reasoning": "low",
          "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": 65.78288863854351,
          "uncertainty": 24.930281974344517,
          "unilateral_faults": 0,
          "wins": 44
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 70,
          "capped_draws": 50,
          "coverage_status": "rated",
          "distinct_rated_opponents": 35,
          "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": "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": 70,
          "raw_elo_rating": 1421.3852147171185,
          "reasoning": "enabled",
          "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": 24.89653094745947,
          "uncertainty": 15.58908290969266,
          "unilateral_faults": 0,
          "wins": 5
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 74,
          "capped_draws": 69,
          "coverage_status": "rated",
          "distinct_rated_opponents": 37,
          "draws": 69,
          "evaluated_setting_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": 3,
          "model": "xiaomi/mimo-v2.5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-5f664f9580459829",
          "rated_matches": 74,
          "raw_elo_rating": 1434.8137881433222,
          "reasoning": "high",
          "reasoning_bracket": "intensive",
          "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "high",
          "repair_status": "repaired",
          "score": 26.641010675069595,
          "uncertainty": 13.985026918962571,
          "unilateral_faults": 0,
          "wins": 2
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 72,
          "capped_draws": 42,
          "coverage_status": "rated",
          "distinct_rated_opponents": 36,
          "draws": 42,
          "evaluated_setting_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": 15,
          "model": "xiaomi/mimo-v2.5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-650d06103e7fa176",
          "rated_matches": 72,
          "raw_elo_rating": 1508.237527612685,
          "reasoning": "enabled",
          "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": 35.272841692532026,
          "uncertainty": 14.770573598065289,
          "unilateral_faults": 0,
          "wins": 15
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 58,
          "capped_draws": 25,
          "coverage_status": "rated",
          "distinct_rated_opponents": 29,
          "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": "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": 32,
          "model": "xiaomi/mimo-v2.5",
          "point_rating_method": "sequential_elo",
          "public_id": "E-b5eb7da0f5021b69",
          "rated_matches": 58,
          "raw_elo_rating": 1296.6805776772846,
          "reasoning": "medium",
          "reasoning_bracket": "balanced",
          "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
          "reasoning_request_mode": "effort",
          "reasoning_setting": "medium",
          "repair_status": "repaired",
          "score": 9.563496475865678,
          "uncertainty": 21.344455490411935,
          "unilateral_faults": 0,
          "wins": 1
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 94,
          "capped_draws": 58,
          "coverage_status": "rated",
          "distinct_rated_opponents": 47,
          "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": "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": 94,
          "raw_elo_rating": 1347.149327600217,
          "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": 16.856581427150502,
          "uncertainty": 7.54891760425771,
          "unilateral_faults": 0,
          "wins": 2
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 90,
          "capped_draws": 72,
          "coverage_status": "rated",
          "distinct_rated_opponents": 45,
          "draws": 72,
          "evaluated_setting_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": 90,
          "raw_elo_rating": 1426.5039592688865,
          "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": 26.160395258498756,
          "uncertainty": 8.664241836095918,
          "unilateral_faults": 0,
          "wins": 2
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 62,
          "capped_draws": 37,
          "coverage_status": "rated",
          "distinct_rated_opponents": 31,
          "draws": 37,
          "evaluated_setting_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-bd1bb7ac29877b8f",
          "rated_matches": 62,
          "raw_elo_rating": 1347.5295489399816,
          "reasoning": "enabled",
          "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": 15.792247386975294,
          "uncertainty": 19.244078834871203,
          "unilateral_faults": 0,
          "wins": 2
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 78,
          "capped_draws": 62,
          "coverage_status": "rated",
          "distinct_rated_opponents": 39,
          "draws": 62,
          "evaluated_setting_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": 78,
          "raw_elo_rating": 1430.648090819964,
          "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": 26.287510609619638,
          "uncertainty": 12.5043950463012,
          "unilateral_faults": 0,
          "wins": 3
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 68,
          "capped_draws": 0,
          "coverage_status": "rated",
          "distinct_rated_opponents": 34,
          "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": 68,
          "raw_elo_rating": 1753.6029652961001,
          "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": 64.20883838011629,
          "uncertainty": 16.4429265428846,
          "unilateral_faults": 0,
          "wins": 50
        },
        {
          "admitted_plugin_count": 1,
          "attempted_matches": 74,
          "capped_draws": 62,
          "coverage_status": "rated",
          "distinct_rated_opponents": 37,
          "draws": 62,
          "evaluated_setting_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": 74,
          "raw_elo_rating": 1427.9759189337483,
          "reasoning": "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": 25.83019830376679,
          "uncertainty": 13.985026918962571,
          "unilateral_faults": 0,
          "wins": 1
        }
      ]
    }
  }
}